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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Schedule
    -0.74
    WORK
    -0.74
    ²¾
    -0.74
    Tu
    -0.69
    -+-+
    -0.68
     Insurance
    -0.66
    SIGN
    -0.66
    ?:
    -0.64
     Legislation
    -0.63
    Union
    -0.62
    POSITIVE LOGITS
    psons
    0.82
    esters
    0.71
    DragonMagazine
    0.69
    aults
    0.67
    merce
    0.63
    dq
    0.63
    ixels
    0.62
    olesc
    0.62
    auts
    0.61
     nails
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.