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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    iov
    -0.86
    ãĥı
    -0.82
    itatively
    -0.75
    º
    -0.75
    dro
    -0.73
    IJ
    -0.73
    MQ
    -0.72
    friends
    -0.72
    UTH
    -0.69
    cler
    -0.67
    POSITIVE LOGITS
    theless
    0.76
     spree
    0.70
     sidel
    0.70
    ylon
    0.70
    urity
    0.69
     separat
    0.68
     releg
    0.67
     disband
    0.66
    nesday
    0.65
    thood
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.