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

    Neuronpedia

    INDEX
    Explanations

    references to data attributes and their values in a dataset

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ris
    -0.14
     Daly
    -0.14
     unl
    -0.14
     Holt
    -0.13
    opia
    -0.13
    ugar
    -0.13
    unan
    -0.13
    .bp
    -0.13
     chords
    -0.13
    ellar
    -0.13
    POSITIVE LOGITS
     Abrams
    0.14
    rift
    0.14
    _rng
    0.14
    ÙģÛĮ
    0.14
    декÑģ
    0.14
    434
    0.13
    pok
    0.13
    itsu
    0.13
    utschen
    0.13
    inant
    0.13
    Act Density 0.003%

    No Known Activations