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

    Neuronpedia

    INDEX
    Explanations

    words related to social and sexual relationships, particularly concerning marriage and LGBTQ+ issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Closure
    -0.77
     mathemat
    -0.76
    ĸļ
    -0.74
     worshipped
    -0.73
    TPP
    -0.71
    kill
    -0.71
     conclud
    -0.71
    thora
    -0.69
     tremend
    -0.67
    arium
    -0.67
    POSITIVE LOGITS
     individuals
    1.53
     persons
    1.40
     adults
    1.27
     youths
    1.25
     households
    1.20
     people
    1.18
     couples
    1.17
     clients
    1.15
     participants
    1.14
     youngsters
    1.14
    Act Density 0.115%

    No Known Activations