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

    Neuronpedia

    INDEX
    Explanations

    numerical values and arithmetic operations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    İstinadlar
    -0.96
    rungsseite
    -0.90
    ſelf
    -0.84
    contentLoaded
    -0.84
     ainfi
    -0.84
    "):
    -0.82
    
    -0.81
     ―――――
    -0.81
     برانيه
    -0.79
     iſt
    -0.79
    POSITIVE LOGITS
     
    0.60
     inter
    0.54
     -
    0.53
    .
    0.53
    ↵↵
    0.52
    <eos>
    0.50
     (
    0.49
     =
    0.47
     entre
    0.46
     Inter
    0.46
    Act Density 0.076%

    No Known Activations