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

    Neuronpedia

    INDEX
    Explanations

    terms related to technology and data processing

    oai_token-act-pair · gpt-3.5-turbo

    references to data structures or terms related to programming and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Instr
    -0.58
     Leilan
    -0.58
     vulner
    -0.57
     referen
    -0.57
     thous
    -0.55
     corrid
    -0.54
     Moroc
    -0.54
    jri
    -0.53
     Vaugh
    -0.52
     Cay
    -0.50
    POSITIVE LOGITS
    lement
    0.68
    mosp
    0.61
    utenant
    0.59
     largeDownload
    0.57
    uscript
    0.53
    ":{"
    0.53
    \":
    0.53
    atibility
    0.53
    tro
    0.52
    tenance
    0.52
    Act Density 0.407%

    No Known Activations