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

    Neuronpedia

    INDEX
    Explanations

    insulting words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    derogatory terms or insults directed at individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     anecd
    -0.80
     proponents
    -0.79
     advocates
    -0.74
    often
    -0.74
     collectively
    -0.73
     Cosponsors
    -0.72
     campaigns
    -0.72
    requently
    -0.71
    Develop
    -0.70
    anwhile
    -0.70
    POSITIVE LOGITS
     whore
    1.33
     fuckin
    1.31
     fucking
    1.26
     girl
    1.25
     cunt
    1.24
     pussy
    1.24
     bitch
    1.23
     dick
    1.20
     goddamn
    1.18
     guy
    1.17
    Act Density 0.547%

    No Known Activations