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

    Neuronpedia

    INDEX
    Explanations

    phrases related to administrative tasks and processes

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation or formatting in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sculpt
    -0.93
     paralle
    -0.84
     spir
    -0.82
     oun
    -0.80
     eleph
    -0.79
     tackling
    -0.78
     stout
    -0.77
     coupled
    -0.77
     myself
    -0.77
     casc
    -0.77
    POSITIVE LOGITS
    Important
    1.73
    FAQ
    1.71
    Example
    1.63
    Types
    1.63
    If
    1.63
    Contact
    1.62
    Information
    1.62
    Please
    1.62
    Examples
    1.61
    Requirements
    1.59
    Act Density 0.305%

    No Known Activations