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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people and companies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    respond
    -0.16
    ãĤ¡
    -0.15
    getic
    -0.15
     succeed
    -0.14
     Blow
    -0.14
    cation
    -0.14
    selves
    -0.13
    ducers
    -0.13
    acebook
    -0.13
     compensate
    -0.13
    POSITIVE LOGITS
    borg
    0.16
    lington
    0.15
    castle
    0.15
    catentry
    0.15
    ©¶æ¥µ
    0.14
    ala
    0.13
    Spring
    0.13
    igham
    0.13
    oland
    0.13
    mund
    0.13
    Act Density 0.008%

    No Known Activations