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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ascade
    -0.75
    sth
    -0.74
    ividual
    -0.73
     acres
    -0.70
    åħī
    -0.69
     hect
    -0.69
    thora
    -0.68
    anski
    -0.68
    sq
    -0.67
    sf
    -0.65
    POSITIVE LOGITS
     thrott
    0.67
    selling
    0.63
     primates
    0.60
    NPR
    0.59
    ener
    0.58
    warming
    0.58
     monkeys
    0.58
     Sora
    0.57
     offending
    0.57
     tampering
    0.56
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.