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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods and question marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     -
    -0.19
    ↵
    -0.19
    -
    -0.18
    anz
    -0.18
     My
    -0.18
    499
    -0.17
    !
    -0.17
    *
    -0.17
    393
    -0.17
     (
    -0.16
    POSITIVE LOGITS
    using
    0.18
    mojom
    0.17
    chandle
    0.17
    бом
    0.16
    ToProps
    0.15
    .DataType
    0.15
    PFN
    0.15
    gamber
    0.15
    )frame
    0.15
    Opcode
    0.15
    Act Density 0.118%

    No Known Activations