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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or section

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

    Punctuation and symbols, particularly ":" and "-"

    np_acts-logits-general · gemini-2.0-flash

    few stone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Majefty
    -0.94
     ExecuteAsync
    -0.86
     myſelf
    -0.85
     Anſ
    -0.85
     fevere
    -0.84
     itſelf
    -0.83
    RenderAtEndOf
    -0.82
    bibinfo
    -0.81
    ſelves
    -0.81
     Houſe
    -0.80
    POSITIVE LOGITS
    ,
    0.55
    <eos>
    0.51
     -
    0.49
     if
    0.48
     v
    0.47
     —
    0.47
     If
    0.47
    -
    0.46
     BytesLike
    0.46
     la
    0.43
    Act Density 0.005%

    No Known Activations