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

    Neuronpedia

    INDEX
    Explanations

    phrases related to moral discussions and debate

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to moral dilemmas and societal impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .]
    -0.63
    rika
    -0.60
     âĵĺ
    -0.60
    .}
    -0.59
    reau
    -0.58
     Smy
    -0.57
     Lydia
    -0.57
    ccording
    -0.56
     largeDownload
    -0.56
    PORT
    -0.56
    POSITIVE LOGITS
    ?),
    0.68
    ?,
    0.65
    ?ãĢį
    0.61
    itia
    0.58
    seq
    0.57
    apon
    0.56
     divest
    0.56
    okane
    0.55
    weeney
    0.55
     commute
    0.54
    Act Density 1.104%

    No Known Activations