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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Bench
    -0.88
    upon
    -0.76
    ween
    -0.73
    XT
    -0.70
    angel
    -0.68
     FW
    -0.65
    Assistant
    -0.64
    ãĥ¯
    -0.63
    arden
    -0.63
    urst
    -0.62
    POSITIVE LOGITS
    azo
    0.76
    emis
    0.73
     IPM
    0.73
    rils
    0.70
    nels
    0.70
    aila
    0.68
     patron
    0.66
    schild
    0.66
     exposures
    0.64
     relief
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.