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

    Neuronpedia

    INDEX
    Explanations

    references to "that," particularly in the context of comparisons or statements involving it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arget
    -0.16
    PRI
    -0.15
    cep
    -0.14
    AZE
    -0.14
    efined
    -0.14
    omit
    -0.14
    ustum
    -0.14
    rat
    -0.13
    ellar
    -0.13
     cop
    -0.13
    POSITIVE LOGITS
    OTO
    0.15
    jen
    0.15
    ylko
    0.14
    yre
    0.14
    lean
    0.14
    GLOBALS
    0.13
    ori
    0.13
     timespec
    0.13
    _subs
    0.13
    zÅij
    0.13
    Act Density 0.043%

    No Known Activations