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

    Neuronpedia

    INDEX
    Explanations

    software version numbers, specifically focusing on the format "x.x.x"

    oai_token-act-pair · gpt-3.5-turbo

    decimal points in numerical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     withd
    -0.84
     purse
    -0.82
     undermin
    -0.79
     enthusi
    -0.77
     bos
    -0.71
     volunte
    -0.71
     entreprene
    -0.70
    ucci
    -0.70
     crocod
    -0.69
     deduct
    -0.69
    POSITIVE LOGITS
    jpg
    0.99
    exe
    0.95
    dylib
    0.93
    txt
    0.92
    0
    0.92
    dll
    0.91
    png
    0.91
    5
    0.87
    prototype
    0.87
    xxx
    0.86
    Act Density 0.193%

    No Known Activations