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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences and data formats

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ✨:
    -0.93
    :✨
    -0.88
    ')))
    -0.86
     '\\;'
    -0.84
    >>()
    -0.83
    -0.82
    '])){
    -0.82
    SpringRunner
    -0.79
    )';
    -0.78
    ')));
    -0.78
    POSITIVE LOGITS
    fü
    0.48
    -
    0.46
    2
    0.44
     Cra
    0.44
     –
    0.44
    GLFW
    0.44
     NO
    0.43
     '
    0.43
     U
    0.42
    เก
    0.42
    Act Density 0.030%

    No Known Activations