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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    }');
    -0.69
    )*/
    -0.65
    ThroughAttribute
    -0.64
    '%(
    -0.63
    '");
    -0.63
     {}));
    -0.63
    verwijspagina
    -0.62
    >*/
    -0.62
     }?>
    -0.62
    }`)
    -0.62
    POSITIVE LOGITS
    :✨
    0.60
     polaire
    0.59
    żesz
    0.59
     Balm
    0.58
    Ancho
    0.56
    Targeting
    0.55
    wezen
    0.55
    ActionCreators
    0.55
     Roz
    0.55
    AndroidJUnit
    0.54
    Act Density 0.288%

    No Known Activations