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

    Neuronpedia

    INDEX
    Explanations

    specific code-related terms and symbols in a programming context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ';
    -0.76
    )');
    -0.73
     ')
    -0.71
    ]';
    -0.66
    '));
    -0.65
    }';
    -0.60
    }`;
    -0.60
     ')[
    -0.60
     Vaz
    -0.60
    .';
    -0.59
    POSITIVE LOGITS
     Tagore
    1.00
    Hentet
    0.93
    ™
    0.84
    unnitel
    0.83
    ttemberg
    0.80
    ômetro
    0.79
     Sodom
    0.77
     bpy
    0.75
    ism
    0.72
     &___
    0.72
    Act Density 0.000%

    No Known Activations