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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.80
     Jagu
    -0.61
     Fraz
    -0.61
     Kant
    -0.60
    ppo
    -0.60
     exclusion
    -0.60
    ibaba
    -0.60
     designation
    -0.59
    asking
    -0.58
    odore
    -0.58
    POSITIVE LOGITS
    hall
    0.83
    ulum
    0.74
    Tact
    0.67
    ::::::::
    0.65
    ICAN
    0.64
    ¯¯¯¯¯¯¯¯
    0.63
    Club
    0.63
    ILS
    0.63
    gran
    0.62
    ican
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.