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

    Neuronpedia

    INDEX
    Explanations

    numerical data or symbols in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    13
    -0.34
    12
    -0.34
    14
    -0.33
     twelve
    -0.32
     thirteen
    -0.30
     Twelve
    -0.30
     fourteen
    -0.29
     tenth
    -0.27
    11
    -0.27
     XII
    -0.27
    POSITIVE LOGITS
    21
    0.36
    20
    0.35
    19
    0.35
    22
    0.33
    23
    0.30
    18
    0.28
     nineteen
    0.27
    Û²Û°
    0.25
    Û²Û±
    0.24
    24
    0.24
    Act Density 0.072%

    No Known Activations