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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    hap
    -0.76
    gyn
    -0.76
    cker
    -0.74
    naire
    -0.73
    cade
    -0.71
    ept
    -0.71
    avin
    -0.70
    azel
    -0.68
    alore
    -0.67
    ubb
    -0.67
    POSITIVE LOGITS
    (_
    0.72
    rists
    0.67
    URRENT
    0.64
     triggers
    0.63
     successors
    0.62
    ENDED
    0.61
     extensions
    0.61
    çīĪ
    0.61
     defect
    0.60
     switches
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.