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

    Neuronpedia

    INDEX
    Explanations

    words related to sexual themes and misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     discorso
    -0.69
    agramm
    -0.65
    jstor
    -0.65
     faveur
    -0.63
     lusso
    -0.63
     Borgo
    -0.60
     Krone
    -0.60
     démo
    -0.59
     îna
    -0.59
     antidote
    -0.58
    POSITIVE LOGITS
     sexual
    2.09
     Sexual
    1.86
    Sexual
    1.84
    sexual
    1.68
     sexually
    1.19
     sexuelle
    0.99
     sexu
    0.90
     seksual
    0.90
     sexuality
    0.88
     sexuales
    0.84
    Act Density 0.035%

    No Known Activations