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

    Neuronpedia

    INDEX
    Explanations

    mentions of questioning or expressing opinions

    oai_token-act-pair · gpt-3.5-turbo

    questions and dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seless
    -0.72
    ©¶æ
    -0.69
    isol
    -0.68
    runs
    -0.67
    imar
    -0.65
     1934
    -0.65
    steen
    -0.65
    CLE
    -0.63
    leg
    -0.62
     buggy
    -0.62
    POSITIVE LOGITS
    .?
    0.83
    topic
    0.80
     moderator
    0.77
     sugg
    0.77
     Explain
    0.77
    ?:
    0.75
    /?
    0.72
     captcha
    0.71
     kb
    0.68
     Void
    0.67
    Act Density 0.493%

    No Known Activations