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

    Neuronpedia

    INDEX
    Explanations

    numerical values and statistical data

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    躇
    -0.75
    $",
    -0.73
     Савезне
    -0.72
     CWE
    -0.71
    ngth
    -0.71
    ACTERS
    -0.71
    daß
    -0.68
     المعيارى
    -0.68
    \"");
    -0.66
    ahead
    -0.65
    POSITIVE LOGITS
    op
    0.53
    pro
    0.50
     fart
    0.49
    po
    0.49
    cl
    0.49
    sel
    0.47
    ver
    0.47
    γ
    0.47
     Yet
    0.46
     تضيفلها
    0.46
    Act Density 0.151%

    No Known Activations