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

    Neuronpedia

    INDEX
    Explanations

    mentions of "confidence intervals" represented by the abbreviation "CI"

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    _^
    -0.84
    remadura
    -0.82
    awaiter
    -0.81
    rrggbb
    -0.77
     خارجية
    -0.77
    Hướng
    -0.76
    zygous
    -0.75
    pushFollow
    -0.75
    RegressionTest
    -0.74
    ufficient
    -0.72
    POSITIVE LOGITS
    ci
    1.34
     ci
    1.17
     Ci
    1.14
     CI
    1.02
    Ci
    1.01
    CI
    0.95
    BASEPATH
    0.91
    cin
    0.88
     sci
    0.88
    sci
    0.88
    Act Density 0.060%

    No Known Activations