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

    Neuronpedia

    INDEX
    Explanations

    questions related to uncertainty or investigation

    oai_token-act-pair · gpt-3.5-turbo

    rhetorical questions and existential queries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.75
    abor
    -0.70
    CTV
    -0.69
    CV
    -0.68
    yssey
    -0.67
    Ãį
    -0.67
    abba
    -0.66
    ruciating
    -0.66
    yk
    -0.65
    venture
    -0.64
    POSITIVE LOGITS
    ?:
    1.28
    ?
    1.18
    ?'
    1.16
    ...?
    1.13
    ?)
    1.10
    ?'"
    1.10
    ?"
    1.08
    ?".
    1.03
    ?).
    1.02
    ?!
    1.01
    Act Density 0.209%

    No Known Activations