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

    Neuronpedia

    INDEX
    Explanations

    references to health-related components or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Observation
    -0.15
     Petit
    -0.15
    lesi
    -0.14
     Verm
    -0.14
    096
    -0.14
    heck
    -0.14
     voksne
    -0.14
    034
    -0.14
     vé
    -0.14
     sis
    -0.14
    POSITIVE LOGITS
     Diss
    0.16
    egasus
    0.16
    kest
    0.15
     )↵↵↵↵↵↵↵↵
    0.14
    WithType
    0.14
    ymax
    0.14
    astle
    0.14
    uros
    0.14
     ogs
    0.14
    ragon
    0.14
    Act Density 0.120%

    No Known Activations