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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating potential actions or permissions related to personal information handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arcy
    -0.18
    adr
    -0.17
    674
    -0.16
    leur
    -0.16
    loi
    -0.14
    adele
    -0.14
    èħ
    -0.14
    mage
    -0.14
    yr
    -0.14
    omo
    -0.14
    POSITIVE LOGITS
    алÑİ
    0.15
    ences
    0.14
     types
    0.14
     freely
    0.14
     ObjectType
    0.14
    à¹ģส
    0.14
    oes
    0.13
    ÎŃÏģ
    0.13
    zelf
    0.13
    etik
    0.13
    Act Density 0.039%

    No Known Activations