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

    Neuronpedia

    INDEX
    Explanations

    words related to performance or quality attributes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vala
    -0.21
    auer
    -0.17
    erer
    -0.16
    éĿł
    -0.16
    ت
    -0.16
    iente
    -0.15
    ulus
    -0.15
    igan
    -0.15
    ances
    -0.15
    ions
    -0.14
    POSITIVE LOGITS
    lesh
    0.22
    olding
    0.19
    aced
    0.19
    lox
    0.19
    obia
    0.18
    olds
    0.17
    usion
    0.17
    ugal
    0.17
    abric
    0.17
    used
    0.17
    Act Density 0.058%

    No Known Activations