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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cedes
    -0.74
    elight
    -0.67
    ocaust
    -0.66
    clusively
    -0.65
    yond
    -0.65
    ategor
    -0.64
    idious
    -0.63
    untarily
    -0.62
    atts
    -0.61
    atical
    -0.61
    POSITIVE LOGITS
    Ear
    0.79
    çĶŁ
    0.71
    FINEST
    0.70
    GH
    0.70
    ILLE
    0.66
    RO
    0.66
    FU
    0.65
    mean
    0.65
    ĺħ
    0.64
    Lat
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.