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

    Neuronpedia

    INDEX
    Explanations

    numerical ratios or comparisons

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gotten
    -0.88
    dream
    -0.80
    sbm
    -0.76
    inelli
    -0.76
     largeDownload
    -0.74
    uggage
    -0.71
    ART
    -0.70
    REAM
    -0.69
    AST
    -0.68
    ORE
    -0.67
    POSITIVE LOGITS
     ratios
    1.10
     ratio
    1.07
    xual
    1.05
    yip
    0.93
     mismatch
    0.87
     numer
    0.86
     imbalance
    0.78
    nces
    0.76
     sum
    0.73
     underestimate
    0.73
    Act Density 0.012%

    No Known Activations