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

    Neuronpedia

    INDEX
    Explanations

    specific naming conventions or identifiers in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocabulary
    -0.16
    ARIABLE
    -0.15
    alue
    -0.15
    ί
    -0.15
    ograd
    -0.14
    ailer
    -0.14
    olume
    -0.14
    _MB
    -0.14
    intage
    -0.14
    anja
    -0.14
    POSITIVE LOGITS
    eur
    0.17
    ël
    0.17
    ech
    0.16
    odore
    0.15
    isle
    0.15
    eral
    0.15
    unda
    0.14
    meer
    0.14
    iki
    0.14
    laus
    0.14
    Act Density 0.150%

    No Known Activations