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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters

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

    Tokens appearing inside parentheses or after commas

    np_acts-logits-general · gemini-2.0-flash

    conjunctions and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -1.01
     myſelf
    -0.96
     houſe
    -0.92
     ſmall
    -0.92
     Monfieur
    -0.92
     purpoſe
    -0.92
     ſeveral
    -0.91
     pleaſure
    -0.89
     greateſt
    -0.88
     ſche
    -0.86
    POSITIVE LOGITS
     and
    1.14
     plus
    0.96
     or
    0.84
    以及
    0.81
    ,
    0.78
    plus
    0.76
     sowie
    0.74
    .
    0.72
    and
    0.71
     also
    0.70
    Act Density 0.762%

    No Known Activations