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

    Neuronpedia

    INDEX
    Explanations

    phrases related to homosexuality

    oai_token-act-pair · gpt-3.5-turbo

    references to homosexuality and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EMS
    -0.83
    Dispatch
    -0.82
    ammy
    -0.75
    GV
    -0.72
    unes
    -0.71
    âĵĺ
    -0.71
    atche
    -0.69
    woods
    -0.69
    ULE
    -0.68
    packs
    -0.66
    POSITIVE LOGITS
    osexual
    1.08
    bian
    0.88
    ity
    0.87
    xual
    0.86
    bians
    0.82
     attracted
    0.78
    ophobic
    0.77
     pedoph
    0.77
    dar
    0.74
    ously
    0.74
    Act Density 0.034%

    No Known Activations