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

    Neuronpedia

    INDEX
    Explanations

    verbs related to exposing or revealing something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "outing" or revealing information about someone's personal aspects, particularly regarding sexuality or secrets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     grooming
    -0.76
     attendant
    -0.68
    ute
    -0.67
     Antar
    -0.64
     stabilize
    -0.62
    uters
    -0.62
    ivan
    -0.62
     deposit
    -0.61
    apy
    -0.60
     oxid
    -0.60
    POSITIVE LOGITS
    casts
    0.93
    numbered
    0.79
    æĢ
    0.79
    cast
    0.77
    outing
    0.76
    stretched
    0.74
    mbuds
    0.73
    selves
    0.72
    olate
    0.71
    liga
    0.71
    Act Density 0.013%

    No Known Activations