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

    Neuronpedia

    INDEX
    Explanations

    nouns and phrases indicating roles or relationships within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     å·Ŀ
    -0.18
    ilen
    -0.16
    uda
    -0.15
    amera
    -0.15
    ascal
    -0.15
    对æĸ¹
    -0.14
    .em
    -0.14
    borough
    -0.14
     putchar
    -0.14
    acd
    -0.13
    POSITIVE LOGITS
    lue
    0.17
    igham
    0.16
    /Dk
    0.16
    ighth
    0.15
    REEN
    0.15
     consumer
    0.15
    reen
    0.14
    .dimension
    0.14
     humans
    0.14
    igy
    0.14
    Act Density 0.053%

    No Known Activations