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

    Neuronpedia

    INDEX
    Explanations

    derogatory terms and phrases that express insults or criticize intelligence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lenker
    -0.75
    DockStyle
    -0.66
    ьаж
    -0.65
     ExecuteAsync
    -0.64
    :✨
    -0.64
    mergeFrom
    -0.62
    ✭✭
    -0.61
    PreferredItem
    -0.61
     Signalez
    -0.60
    aspectj
    -0.58
    POSITIVE LOGITS
     stupid
    1.83
    stupid
    1.65
     dumb
    1.63
     Stupid
    1.58
    Stupid
    1.54
     idiot
    1.53
     foolish
    1.53
     stupidity
    1.50
     idiotic
    1.44
    dumb
    1.43
    Act Density 0.428%

    No Known Activations