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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Werewolf
    -0.77
     Halls
    -0.74
     Gleaming
    -0.72
     Flare
    -0.72
     Hole
    -0.69
     Era
    -0.66
     Zeal
    -0.63
     Examiner
    -0.63
     Dong
    -0.63
     Hearing
    -0.62
    POSITIVE LOGITS
    Reviewer
    1.00
    ="#
    0.77
    utical
    0.76
    anon
    0.75
    ModLoader
    0.74
    acl
    0.73
    tel
    0.70
    icals
    0.69
     constitu
    0.69
    iberal
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.