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

    Neuronpedia

    INDEX
    Explanations

    adjectives and phrases that indicate quality or excellence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .dsl
    -0.17
    _stdio
    -0.16
     Became
    -0.15
     withdrew
    -0.14
    InParameter
    -0.14
    IMIZE
    -0.13
    lobals
    -0.13
    &uuml
    -0.13
    anvas
    -0.13
     froze
    -0.13
    POSITIVE LOGITS
     written
    0.30
    -exec
    0.29
     crafted
    0.28
     executed
    0.28
    -written
    0.28
     thought
    0.27
     wrought
    0.27
     constructed
    0.26
     done
    0.26
    exec
    0.25
    Act Density 0.058%

    No Known Activations