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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific numerical values, especially in a historical or legal context

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

    years and decades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.51
    xiv
    -0.40
     bureaus
    -0.40
    ůli
    -0.40
     alts
    -0.38
    XmlElement
    -0.36
    xii
    -0.36
     flan
    -0.35
     beamed
    -0.35
     Viv
    -0.34
    POSITIVE LOGITS
     houſe
    0.71
    ſelves
    0.66
     ſever
    0.66
    ſelf
    0.64
     feroit
    0.63
     myſelf
    0.63
     auroit
    0.63
     avoient
    0.62
     leaſt
    0.61
     ainfi
    0.61
    Act Density 0.023%

    No Known Activations