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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Angels
    -0.70
     angels
    -0.70
    birds
    -0.65
     Defendants
    -0.63
    stories
    -0.60
    VALUE
    -0.60
    communications
    -0.59
    ths
    -0.59
     Riders
    -0.59
    seller
    -0.58
    POSITIVE LOGITS
     redes
    0.78
     tremend
    0.77
     exting
    0.76
     exha
    0.76
    rily
    0.75
    ophon
    0.74
    ktop
    0.74
    onga
    0.73
    bledon
    0.71
    olor
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.