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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to construction or development

    oai_token-act-pair · gpt-3.5-turbo

    terms related to software or hardware builds and versions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izon
    -0.86
    mia
    -0.85
     Lauder
    -0.77
    ican
    -0.75
    mic
    -0.73
    romeda
    -0.73
    ricular
    -0.68
    utical
    -0.68
    nton
    -0.67
    ppe
    -0.67
    POSITIVE LOGITS
    smanship
    0.76
    packs
    0.75
     decks
    0.73
    offs
    0.72
    raft
    0.70
     suspense
    0.70
    strap
    0.68
    built
    0.67
     builds
    0.67
     kits
    0.66
    Act Density 0.033%

    No Known Activations