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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     proprement
    -0.45
     clar
    -0.44
    澄
    -0.44
     mort
    -0.44
    tissa
    -0.44
    PECT
    -0.43
    追
    -0.43
    نگار
    -0.43
     chức
    -0.42
    Toda
    -0.42
    POSITIVE LOGITS
     random
    1.63
     randomly
    1.61
     Random
    1.52
    Random
    1.52
    random
    1.45
     RANDOM
    1.40
     randomness
    1.31
    RANDOM
    1.28
     randomized
    1.26
     randomization
    1.23
    Act Density 0.412%

    No Known Activations