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

    Neuronpedia

    INDEX
    Explanations

    references to JSON-based data structures and their manipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .dk
    -0.14
    Ñİк
    -0.14
    older
    -0.13
     Dudley
    -0.13
    ixin
    -0.13
    _ASSUME
    -0.13
    ziej
    -0.13
    วà¸Ķ
    -0.13
    erli
    -0.13
    psc
    -0.12
    POSITIVE LOGITS
     .
    0.23
    !.
    0.17
    ?.
    0.14
     Sphere
    0.14
     .↵
    0.14
     equival
    0.14
    serrat
    0.14
     Tucker
    0.13
     "
    0.13
    ..
    0.13
    Act Density 0.083%

    No Known Activations