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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Cul
    -0.67
     colle
    -0.65
     subsidized
    -0.65
     Guarant
    -0.63
     bureau
    -0.62
     promised
    -0.62
     Bav
    -0.62
     Revenue
    -0.61
    ACTED
    -0.61
     relief
    -0.60
    POSITIVE LOGITS
    phe
    0.78
    TPP
    0.76
    GMT
    0.76
    enstein
    0.74
    doi
    0.74
    oqu
    0.74
    URI
    0.73
    eneg
    0.71
    BALL
    0.70
    ype
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.