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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Annotations
    -0.78
    trap
    -0.66
    Reviewer
    -0.66
    wra
    -0.64
     rese
    -0.63
    Cover
    -0.63
     prevented
    -0.61
     looph
    -0.61
     outstanding
    -0.59
     extension
    -0.58
    POSITIVE LOGITS
    eve
    0.82
    peak
    0.81
    achusetts
    0.77
    emen
    0.77
    edom
    0.77
    orial
    0.76
    iple
    0.74
    eto
    0.72
    aturday
    0.71
    eton
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.