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

    Neuronpedia

    INDEX
    Explanations

    phrases or questions related to uncertainty and speculation

    oai_token-act-pair · gpt-3.5-turbo

    instances of questioning, speculation, or uncertainty in a conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yk
    -0.78
    ruciating
    -0.71
    ©¶æ¥µ
    -0.70
    yssey
    -0.68
    abba
    -0.67
    CTV
    -0.66
    inery
    -0.66
    zar
    -0.65
    CV
    -0.65
    yrights
    -0.63
    POSITIVE LOGITS
    ?:
    1.44
    ?
    1.28
    ?'
    1.26
    ?)
    1.25
    ...?
    1.24
    ?).
    1.21
    ?",
    1.17
    ?,
    1.17
    ?'"
    1.16
    ?"
    1.15
    Act Density 0.316%

    No Known Activations