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

    Neuronpedia

    INDEX
    Explanations

    descriptions of relationships between people, often involving dating

    oai_token-act-pair · gpt-3.5-turbo

    references to romantic relationships and dating experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MN
    -0.81
    phabet
    -0.80
    imble
    -0.76
    ggle
    -0.74
    itivity
    -0.72
    gement
    -0.72
     Blizz
    -0.71
    TPPStreamerBot
    -0.71
    Protect
    -0.70
    £ı
    -0.69
    POSITIVE LOGITS
     prostitute
    1.81
     prostitutes
    1.67
     mistress
    1.47
     girlfriends
    1.41
     whore
    1.40
     prostitution
    1.35
     waitress
    1.32
     actresses
    1.31
     maid
    1.27
     glamorous
    1.26
    Act Density 0.517%

    No Known Activations