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

    Neuronpedia

    INDEX
    Explanations

    specific definite articles and personal pronouns that indicate identity or involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    visor
    -0.15
    orks
    -0.15
    isseur
    -0.14
    ocaust
    -0.14
    ê³
    -0.14
    vation
    -0.14
     Crus
    -0.14
    erken
    -0.14
    eyse
    -0.14
     concent
    -0.13
    POSITIVE LOGITS
     collateral
    0.15
    364
    0.15
    ford
    0.15
    gal
    0.14
    215
    0.14
    164
    0.14
    λά
    0.14
    311
    0.14
    itan
    0.14
     bef
    0.14
    Act Density 0.002%

    No Known Activations