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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    opsis
    -0.84
    ão
    -0.70
    ®
    -0.68
    ĻĤ
    -0.66
    CHAT
    -0.64
    peak
    -0.63
    edu
    -0.61
    Unity
    -0.61
    ĨĴ
    -0.60
    antes
    -0.60
    POSITIVE LOGITS
    gem
    0.76
    jriwal
    0.73
     IRA
    0.71
    inois
    0.68
     Leafs
    0.67
    itty
    0.67
     Flames
    0.64
    addy
    0.63
    itatively
    0.62
    renheit
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.