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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bombings
    -0.74
     extremism
    -0.69
    Nunca
    -0.68
    Casi
    -0.68
    Siempre
    -0.67
    Muchos
    -0.67
    findOrFail
    -0.66
    Incluso
    -0.65
    ilitary
    -0.65
     militants
    -0.64
    POSITIVE LOGITS
    <bos>
    8.04
     perfet
    1.85
     encomp
    1.80
     dispen
    1.79
     intersper
    1.76
     affor
    1.76
     guarante
    1.75
     ?...
    1.74
     excu
    1.73
     eyel
    1.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.