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

    Neuronpedia

    INDEX
    Explanations

    instances of inconsistent or contradictory behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rray
    -0.15
    celik
    -0.15
    Äħd
    -0.15
     /**<
    -0.14
    unger
    -0.14
    lichkeit
    -0.14
     accessor
    -0.14
     //!<
    -0.14
    Äįem
    -0.14
    osition
    -0.14
    POSITIVE LOGITS
    unic
    0.16
    ascus
    0.14
     TORT
    0.14
    .getOwnProperty
    0.14
     GenerationType
    0.14
    swagen
    0.14
    unicorn
    0.14
     cables
    0.13
    infer
    0.13
    isify
    0.13
    Act Density 0.009%

    No Known Activations