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

    Neuronpedia

    INDEX
    Explanations

    sentences that express personal experiences or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    од
    -0.55
    up
    -0.55
     ندار
    -0.51
     =
    -0.48
    has
    -0.47
    UP
    -0.46
     Gans
    -0.45
    out
    -0.45
     just
    -0.45
     skor
    -0.44
    POSITIVE LOGITS
    NewUrlParser
    0.86
     فريبيس
    0.82
    tvguidetime
    0.80
     ujednoznacz
    0.79
    abetes
    0.77
    TagMode
    0.74
    atoga
    0.74
    UserScript
    0.74
    évaluateur
    0.74
     TextInputType
    0.73
    Act Density 0.199%

    No Known Activations