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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "openly" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "openly" and contexts related to public admissions or expressions of identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesota
    -0.79
    ocre
    -0.74
    ĸļ
    -0.73
    akeru
    -0.69
    ammy
    -0.68
    oday
    -0.68
    =-=-=-=-=-=-=-=-
    -0.68
     Summoner
    -0.67
     Tune
    -0.67
     Karma
    -0.66
    POSITIVE LOGITS
     bisexual
    0.82
    odox
    0.82
     confess
    0.81
    obin
    0.78
     admit
    0.77
     gay
    0.77
    lishing
    0.77
     contradicted
    0.77
     openly
    0.76
     disreg
    0.76
    Act Density 0.017%

    No Known Activations