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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "accept" and related terms, such as "accepted," "accepting," and "acceptance."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    TextFormField
    -0.61
    ("]");
    -0.52
    CascadeType
    -0.50
    ("-");
    -0.48
    PROTO
    -0.48
    P
    -0.47
    SizeMode
    -0.47
    citenamefont
    -0.47
    Мо
    -0.46
    WriteHeader
    -0.45
    POSITIVE LOGITS
     milf
    1.26
     depic
    1.23
     Accepting
    1.21
     snoopy
    1.21
     volunte
    1.19
     acce
    1.16
     shenan
    1.16
     hentai
    1.15
     reluct
    1.12
     maneu
    1.12
    Act Density 0.091%

    No Known Activations