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

    Neuronpedia

    INDEX
    Explanations

    inappropriate language or offensive terms

    oai_token-act-pair · gpt-3.5-turbo

    intense emotional expressions, particularly those involving strong profanity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ère
    -0.76
    Msg
    -0.76
    Folder
    -0.74
    anu
    -0.73
    BIL
    -0.72
    laus
    -0.71
    lication
    -0.70
    NetMessage
    -0.70
    inel
    -0.69
    ilus
    -0.69
    POSITIVE LOGITS
     kidding
    0.95
     fucking
    0.89
     fuck
    0.82
     asshole
    0.81
     bast
    0.81
     goddamn
    0.80
     shit
    0.78
     idiots
    0.75
     dick
    0.75
     fuckin
    0.75
    Act Density 0.027%

    No Known Activations