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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "play" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.46
     Monfieur
    -1.36
     itſelf
    -1.34
     ―――――
    -1.24
     myſelf
    -1.23
     ſeveral
    -1.14
     Reſ
    -1.13
     pleaſure
    -1.13
     Houſe
    -1.12
     becauſe
    -1.12
    POSITIVE LOGITS
     (
    0.82
    ,
    0.75
     in
    0.75
    ?
    0.74
     the
    0.71
     
    0.70
    .
    0.70
     so
    0.68
     I
    0.68
     come
    0.68
    Act Density 0.181%

    No Known Activations