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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    dar
    -0.73
    clair
    -0.73
     Juda
    -0.71
    manuel
    -0.68
    cit
    -0.67
    ãĥĵ
    -0.66
    alk
    -0.65
    cies
    -0.65
    kay
    -0.65
     Perspect
    -0.65
    POSITIVE LOGITS
    enance
    0.66
     CODE
    0.63
    oxicity
    0.63
    idy
    0.62
    oxic
    0.61
    amins
    0.61
    YP
    0.60
     attacker
    0.59
     bribery
    0.59
    ++)
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.