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

    Neuronpedia

    INDEX
    Explanations

    references to notable individuals and their contributions or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ts
    -0.13
    tf
    -0.10
    tas
    -0.10
    ta
    -0.10
    eer
    -0.10
    tm
    -0.10
    hs
    -0.10
    ti
    -0.10
    tem
    -0.10
    te
    -0.09
    POSITIVE LOGITS
    (es
    0.19
    ’
    0.12
    sing
    0.11
    ness
    0.11
    '
    0.11
    ses
    0.11
    es
    0.10
    phere
    0.10
    esModule
    0.10
    dom
    0.09
    Act Density 0.478%

    No Known Activations