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

    Neuronpedia

    INDEX
    Explanations

    references to statistical slopes in research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.79
     nakalista
    -0.78
    jmniej
    -0.72
     كمان
    -0.64
    bantu
    -0.63
    criter
    -0.62
     Argonne
    -0.61
     ENERG
    -0.60
     Sesame
    -0.59
    dued
    -0.59
    POSITIVE LOGITS
     slope
    0.72
     Fisher
    0.66
     slopes
    0.61
     hashlib
    0.60
    slope
    0.59
     Je
    0.57
    Fisher
    0.57
     replicated
    0.56
     stocks
    0.56
     Slope
    0.55
    Act Density 0.213%

    No Known Activations