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

    Neuronpedia

    INDEX
    Explanations

    phrases regarding permission and copyright restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Requires permission

    np_acts-logits-general · gemini-2.0-flash

    without permission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    참고
    -0.62
    </thead>
    -0.61
    OOTDTY
    -0.59
     незавершена
    -0.56
     ویکی‌پدیای
    -0.56
     itſelf
    -0.54
    abstractmethod
    -0.54
     IBOutlet
    -0.51
     numberWith
    -0.51
    出版年
    -0.51
    POSITIVE LOGITS
     permission
    1.93
     consent
    1.76
     Permission
    1.55
    permission
    1.51
    Permission
    1.40
    consent
    1.39
     Consent
    1.37
    Consent
    1.32
     approval
    1.30
     permissions
    1.29
    Act Density 0.329%

    No Known Activations