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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "any" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pe
    -0.18
     stuff
    -0.17
    po
    -0.16
    less
    -0.16
    laden
    -0.15
    etailed
    -0.14
    uren
    -0.14
    ste
    -0.14
    chio
    -0.14
     more
    -0.14
    POSITIVE LOGITS
    /all
    0.23
    combination
    0.20
     given
    0.20
     combination
    0.20
    THING
    0.20
    /e
    0.19
     GIVEN
    0.19
     kind
    0.19
    where
    0.18
    given
    0.18
    Act Density 0.058%

    No Known Activations