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

    Neuronpedia

    INDEX
    Explanations

    specialized technical terms and their usage in a contextual manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isches
    -0.18
    rego
    -0.18
    езда
    -0.17
    loha
    -0.16
    ä¸ĬçļĦ
    -0.16
    кого
    -0.16
    ä¸ĭçļĦ
    -0.16
    era
    -0.16
    éĩĮçļĦ
    -0.16
    ового
    -0.15
    POSITIVE LOGITS
    ении
    0.38
    лении
    0.37
    ании
    0.37
    алÑĮном
    0.34
    нике
    0.31
    енном
    0.31
    ÑģÑĤве
    0.31
    ине
    0.28
    Ñģком
    0.27
    ÑĢии
    0.26
    Act Density 0.031%

    No Known Activations