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

    Neuronpedia

    INDEX
    Explanations

    punctuation and structural elements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .guard
    -0.14
    zes
    -0.14
    cu
    -0.13
     Compensation
    -0.13
    cue
    -0.13
    ../../../
    -0.13
    ansas
    -0.13
    annis
    -0.13
    оÑĩно
    -0.12
    ิà¸Ķà¸ķ
    -0.12
    POSITIVE LOGITS
    eson
    0.14
    ptime
    0.14
    bia
    0.14
    Prosec
    0.14
    oard
    0.14
    JECTED
    0.13
    λί
    0.13
    /libs
    0.13
    lij
    0.13
    eya
    0.13
    Act Density 0.559%

    No Known Activations