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

    Neuronpedia

    INDEX
    Explanations

    expressions related to mathematical limits and thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    “
    -0.67
    boj
    -0.65
    ”
    -0.61
     dirig
    -0.60
     ejec
    -0.59
     skyl
    -0.59
    =”
    -0.57
    row
    -0.56
     Hek
    -0.56
     “
    -0.55
    POSITIVE LOGITS
    varepsilon
    1.78
     epsilon
    1.76
    epsilon
    1.69
     Epsilon
    1.52
     ε
    1.52
    Epsilon
    1.41
    ε
    1.38
    ϵ
    1.19
     ɛ
    1.17
    psilon
    1.15
    Act Density 0.121%

    No Known Activations