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

    Neuronpedia

    INDEX
    Explanations

    phrases and words that indicate negativity, harm, or adverse conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndPassword
    -0.16
    eding
    -0.16
    posable
    -0.16
    /cal
    -0.14
     AW
    -0.14
    اÙģÙĬØ©
    -0.14
    agnitude
    -0.14
    iente
    -0.13
    endon
    -0.13
    uest
    -0.13
    POSITIVE LOGITS
    /problem
    0.19
    rous
    0.18
    indre
    0.17
    /null
    0.17
     Stap
    0.15
    ÙĪÙĦا
    0.15
    umper
    0.14
    erp
    0.14
    ordes
    0.14
    ger
    0.14
    Act Density 0.233%

    No Known Activations