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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    apeake
    -0.85
    fire
    -0.75
    ially
    -0.75
    oland
    -0.73
    esan
    -0.65
    orage
    -0.64
    daq
    -0.64
    tle
    -0.62
    olate
    -0.62
    mal
    -0.61
    POSITIVE LOGITS
    ategory
    0.69
     Herm
    0.68
    steen
    0.63
     Reply
    0.61
     skelet
    0.60
     boxed
    0.60
    borg
    0.58
     crotch
    0.58
     suspic
    0.57
     indemn
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.