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

    Neuronpedia

    INDEX
    Explanations

    evidence or examples that support specific claims or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.82
    ImageContext
    -0.78
    ########.
    -0.75
    JpaRepository
    -0.75
    NameInMap
    -0.75
    ThroughAttribute
    -0.72
     AssemblyVersion
    -0.71
    Vidite
    -0.71
    DeleteBehavior
    -0.70
    UserScript
    -0.70
    POSITIVE LOGITS
     example
    0.64
     evidenced
    0.60
     evidence
    0.54
     ejemplos
    0.51
     witness
    0.51
     examples
    0.49
    ']").
    0.48
     exemples
    0.48
     demonstrated
    0.48
     recent
    0.47
    Act Density 0.471%

    No Known Activations