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

    Neuronpedia

    INDEX
    Explanations

    references to legal or regulatory items and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     --
    -0.24
     Via
    -0.16
     –
    -0.15
     بÙĢ
    -0.14
    Via
    -0.14
     via
    -0.14
    via
    -0.14
    ):?>↵
    -0.14
     -
    -0.14
     ->
    -0.14
    POSITIVE LOGITS
    —↵↵
    0.27
     —↵
    0.26
     subsection
    0.23
     —↵↵
    0.23
    —
    0.22
    ,—
    0.21
    -č↵
    0.20
    ”—
    0.20
    ————
    0.19
    ——
    0.19
    Act Density 0.011%

    No Known Activations