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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    xual
    -0.93
    [/
    -0.82
    ÃŁ
    -0.74
    Fine
    -0.74
    ctors
    -0.73
    aber
    -0.72
    pex
    -0.67
    isodes
    -0.66
    Mech
    -0.66
    ãĥ¯
    -0.66
    POSITIVE LOGITS
     charter
    0.69
    chell
    0.68
    andum
    0.68
    aeus
    0.66
    intosh
    0.65
     Emanuel
    0.65
     Lynn
    0.64
     convict
    0.63
    acist
    0.62
     relay
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.