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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Britons
    -0.73
     feats
    -0.62
     Tanz
    -0.62
     curfew
    -0.62
    otos
    -0.61
    bara
    -0.61
     Fenrir
    -0.61
     thresholds
    -0.60
     flares
    -0.60
    romeda
    -0.60
    POSITIVE LOGITS
    intend
    0.76
    OY
    0.74
    itud
    0.72
    drawn
    0.72
    laughter
    0.71
    onomic
    0.70
    DAQ
    0.70
    QL
    0.70
    ilty
    0.69
    JV
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.