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

    Neuronpedia

    INDEX
    Explanations

    instances of physical intimacy and sexual situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tikang
    -0.44
     sag
    -0.41
    UDP
    -0.41
     Medals
    -0.40
     pitting
    -0.39
     deur
    -0.38
    Život
    -0.38
     Mantle
    -0.38
    humanité
    -0.38
     gyhoeddwyd
    -0.38
    POSITIVE LOGITS
    ьажоргаш
    0.56
    exitRule
    0.53
     otomatig
    0.48
    featureID
    0.47
    ScopeManager
    0.47
     sensual
    0.46
     sexy
    0.45
    pova
    0.44
     erotic
    0.43
    ✷
    0.43
    Act Density 0.261%

    No Known Activations