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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cellence
    -0.69
    ¬¼
    -0.65
     Terrorism
    -0.64
     Helic
    -0.63
    ivari
    -0.62
     Hezbollah
    -0.61
    Boo
    -0.61
     CCTV
    -0.61
     mater
    -0.60
     typh
    -0.59
    POSITIVE LOGITS
    gars
    0.78
    İĭ
    0.73
    chin
    0.73
    older
    0.73
    aphael
    0.72
    odes
    0.72
    jan
    0.71
     cf
    0.71
    redits
    0.68
     Siber
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.