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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and codes related to organizations, products, or technical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbn
    -0.18
    oftware
    -0.15
    oft
    -0.14
    ogne
    -0.14
    /or
    -0.14
    ão
    -0.14
    axe
    -0.14
    Evaluator
    -0.14
    ettle
    -0.14
    e
    -0.14
    POSITIVE LOGITS
    sWith
    0.16
    spo
    0.15
    esus
    0.14
    fried
    0.14
    ewise
    0.14
    ROLE
    0.13
    ANGO
    0.13
    ÙĪØŃ
    0.13
    .Aggressive
    0.13
    plusplus
    0.13
    Act Density 0.538%

    No Known Activations