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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names preceded by a single capital letter "T"

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific token representing the end of text or line

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.71
     ment
    -0.66
     diapers
    -0.66
     cannabin
    -0.63
     visuals
    -0.60
    TPPStreamerBot
    -0.59
     Arctic
    -0.59
     Atmosp
    -0.59
     Witcher
    -0.59
     destro
    -0.59
    POSITIVE LOGITS
    ARGET
    1.41
    ractor
    1.20
    ract
    1.17
    ravis
    1.16
    ribute
    1.13
    ottenham
    1.13
    EMP
    1.13
    empt
    1.13
    ruly
    1.13
    eddy
    1.10
    Act Density 0.040%

    No Known Activations