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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ensis
    -0.73
    letters
    -0.69
    rehend
    -0.67
    eline
    -0.66
    este
    -0.66
    ACTED
    -0.64
    sth
    -0.64
    EEP
    -0.64
     Hungry
    -0.63
    enges
    -0.63
    POSITIVE LOGITS
     Kaz
    0.68
     viewer
    0.66
    igious
    0.65
    rero
    0.64
    asking
    0.61
    hod
    0.59
    é»Ĵ
    0.58
     prom
    0.58
     Siren
    0.58
     polyg
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.