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

    Neuronpedia

    INDEX
    Explanations

    occurrences of a specific word, 'Pad', in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pad" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    naires
    -0.66
     Ultron
    -0.63
     Frankenstein
    -0.63
     Samar
    -0.63
     VIDEOS
    -0.60
     Heller
    -0.59
     Sheen
    -0.58
     bystand
    -0.58
     Colossus
    -0.57
    esse
    -0.57
    POSITIVE LOGITS
    awan
    1.40
    lock
    1.18
    locks
    1.05
    locked
    1.03
    het
    1.02
    geon
    0.93
    rice
    0.91
    locking
    0.89
     Thai
    0.88
    arity
    0.87
    Act Density 0.036%

    No Known Activations