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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rition
    -0.89
     Hebdo
    -0.68
     Directorate
    -0.66
    packs
    -0.63
     Stability
    -0.63
    uca
    -0.62
     Marino
    -0.61
     Victims
    -0.61
    ulative
    -0.60
    qv
    -0.59
    POSITIVE LOGITS
    umbnails
    0.77
     afar
    0.74
     sleeve
    0.65
    zos
    0.64
    Es
    0.64
    acus
    0.63
     rent
    0.63
     syn
    0.62
    Jr
    0.62
    Topic
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.