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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Sharif
    -0.84
    atari
    -0.71
     Aura
    -0.65
    llah
    -0.64
    ahi
    -0.63
     Winds
    -0.63
    FIELD
    -0.62
    Army
    -0.61
     Frie
    -0.60
    arb
    -0.60
    POSITIVE LOGITS
    nov
    0.73
     recogn
    0.73
    ceptions
    0.69
    lege
    0.67
    namese
    0.66
    hap
    0.65
    ractions
    0.65
    anova
    0.65
    riction
    0.65
    initely
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.