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

    Neuronpedia

    INDEX
    Explanations

    references to types of organizational identifiers or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ervo
    -0.23
    auce
    -0.20
    zek
    -0.19
    atz
    -0.19
    erv
    -0.19
    peak
    -0.18
    upper
    -0.17
    okol
    -0.17
    aid
    -0.17
    ources
    -0.16
    POSITIVE LOGITS
    onym
    0.19
    bsub
    0.18
    ELLOW
    0.15
    artner
    0.15
    plex
    0.15
    ầm
    0.15
    otec
    0.15
    uentes
    0.15
    ellow
    0.14
    ÑģÑĤÑĢи
    0.14
    Act Density 0.064%

    No Known Activations