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

    Neuronpedia

    INDEX
    Explanations

    phrases related to questioning or making statements about various subjects

    oai_token-act-pair · gpt-3.5-turbo

    questions related to accountability and critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yssey
    -0.85
    ©¶æ¥µ
    -0.82
    inery
    -0.74
    yk
    -0.72
    CV
    -0.71
    imil
    -0.69
    enez
    -0.67
    Ire
    -0.67
    accompanied
    -0.67
    20439
    -0.67
    POSITIVE LOGITS
    ?:
    1.39
    ?'
    1.32
    ?
    1.28
    ?"
    1.27
    ?",
    1.27
    ?".
    1.27
    ?'"
    1.27
    ?)
    1.25
    ?).
    1.22
    ...?
    1.20
    Act Density 0.321%

    No Known Activations