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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific measurements and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gibbs
    -0.17
     Tune
    -0.16
    ména
    -0.15
    lotte
    -0.14
    лаÑĤи
    -0.14
    uario
    -0.14
    une
    -0.14
    amer
    -0.14
    ılı
    -0.13
    ickness
    -0.13
    POSITIVE LOGITS
    edBy
    0.32
    ed
    0.27
    edException
    0.18
    alyzed
    0.16
    stered
    0.16
    ised
    0.16
    ened
    0.16
    ted
    0.16
    ieved
    0.15
    able
    0.15
    Act Density 0.131%

    No Known Activations