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

    Neuronpedia

    INDEX
    Explanations

    words related to romantic relationships and dating

    oai_token-act-pair · gpt-3.5-turbo

    references to dating and romantic relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raq
    -0.87
    ucky
    -0.81
    uckles
    -0.80
    aug
    -0.77
    acca
    -0.72
    owder
    -0.72
    psey
    -0.72
     sidx
    -0.69
    ascade
    -0.68
    uador
    -0.66
    POSITIVE LOGITS
     dating
    1.20
     Dating
    1.17
    dating
    0.80
     monog
    0.79
    ĸļ
    0.76
     Tinder
    0.75
     dated
    0.71
    thood
    0.69
     Surviv
    0.68
     Dates
    0.67
    Act Density 0.007%

    No Known Activations