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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    odan
    -0.68
     "$:/
    -0.67
    imens
    -0.62
    abre
    -0.62
     dracon
    -0.61
    roman
    -0.61
    ilitary
    -0.59
    athered
    -0.58
     Daylight
    -0.58
    inki
    -0.58
    POSITIVE LOGITS
    RESULTS
    0.71
     Rouhani
    0.66
    NAS
    0.65
    IQ
    0.65
    caster
    0.65
     DISTR
    0.65
    itsch
    0.63
    hips
    0.62
     Computing
    0.61
    uve
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.