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

    Neuronpedia

    INDEX
    Explanations

    negative assessments or criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    де
    -0.15
    aze
    -0.15
    梨
    -0.14
    _DRIVE
    -0.14
    fade
    -0.14
    709
    -0.14
    оÑĩек
    -0.14
    ูร
    -0.13
    urity
    -0.13
    amburger
    -0.13
    POSITIVE LOGITS
     by
    0.22
    andest
    0.16
    edBy
    0.16
    Sock
    0.15
    quest
    0.15
    .gov
    0.15
     repe
    0.14
    by
    0.14
    sock
    0.14
     تÙĪسط
    0.14
    Act Density 0.192%

    No Known Activations