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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to computer science and technology

    oai_token-act-pair · gpt-3.5-turbo

    instances of an empty string or represent a non-specific placeholder

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exha
    -0.61
     vacancy
    -0.59
     Trib
    -0.59
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.59
     ment
    -0.59
     Witch
    -0.59
     quotes
    -0.57
     rounding
    -0.57
     lax
    -0.57
    Ĥİ
    -0.57
    POSITIVE LOGITS
    ARGET
    1.47
    reatment
    1.32
    ottenham
    1.29
    olerance
    1.28
    OTAL
    1.26
    ruly
    1.25
    ribute
    1.22
    ravis
    1.20
    icket
    1.20
    oward
    1.20
    Act Density 0.046%

    No Known Activations