Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    quantitative data and statistics related to studies or research.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    features or characteristics of academic research articles.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases that introduce contrasting or additional points, particularly "On the one hand" and "On the other hand", as well as similar phrases like "On top of that" or "On average".

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Following the word "on"

    np_acts-logits-general · gemini-2.0-flash

    on phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ModelSerializer
    -0.68
    ManagedBean
    -0.67
    ########.
    -0.63
    endregion
    -0.58
    offsetof
    -0.58
    BindingResult
    -0.58
    EReference
    -0.57
    Jereo
    -0.56
    thansa
    -0.56
    jooq
    -0.56
    POSITIVE LOGITS
     behalf
    1.78
     occasion
    0.94
     top
    0.88
     account
    0.81
    omato
    0.76
    cological
    0.75
     the
    0.74
     board
    0.73
     horseback
    0.72
     average
    0.72
    Act Density 0.429%

    No Known Activations