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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ħ¢
    -0.73
    dit
    -0.73
     Devi
    -0.65
     Niet
    -0.64
     Welch
    -0.63
    rine
    -0.63
    ulous
    -0.63
     Jere
    -0.63
    iquette
    -0.61
    owship
    -0.61
    POSITIVE LOGITS
     Adv
    0.73
    same
    0.69
    hend
    0.69
    address
    0.67
    chair
    0.65
    Washington
    0.63
    Asian
    0.60
    smoking
    0.59
     Advance
    0.58
    stop
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.