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

    Neuronpedia

    INDEX
    Explanations

    references to policy types in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ([↵
    -0.19
    :[[
    -0.19
    (['
    -0.17
    (["
    -0.17
    ]["
    -0.16
    ][(
    -0.16
    ']['
    -0.16
    "]["
    -0.15
     [['
    -0.15
    Poster
    -0.15
    POSITIVE LOGITS
     [
    0.32
    [
    0.25
    \[
    0.16
    __[
    0.14
    _OCCURRED
    0.14
    isObject
    0.14
    wand
    0.14
    unya
    0.14
    anship
    0.14
    incare
    0.14
    Act Density 0.097%

    No Known Activations