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

    Neuronpedia

    INDEX
    Explanations

    references to total quantities or counts in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     typelib
    -0.77
     Lemonade
    -0.63
    ếng
    -0.61
     Vuitton
    -0.61
    pertise
    -0.61
    bibinfo
    -0.60
     TextAppearance
    -0.59
    Таким
    -0.57
     sealant
    -0.57
     myſelf
    -0.57
    POSITIVE LOGITS
     &___
    0.73
     linkovi
    0.55
     виправивши
    0.55
    ArgsConstructor
    0.54
    Din
    0.53
    xos
    0.52
     ProtoMessage
    0.51
     فريبيس
    0.51
    PropertyChanging
    0.50
     estimés
    0.50
    Act Density 0.008%

    No Known Activations