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

    Neuronpedia

    INDEX
    Explanations

    references to corporate promises and their fulfillment or failure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favorable
    -0.20
    avior
    -0.19
     neighboring
    -0.18
     unfavorable
    -0.18
     flavored
    -0.18
     neighbors
    -0.18
     defense
    -0.18
     catalogs
    -0.17
     colored
    -0.17
     rumored
    -0.17
    POSITIVE LOGITS
     vot
    0.15
    ular
    0.15
    MF
    0.14
     RSS
    0.14
     Bengal
    0.14
    /crypto
    0.14
    utt
    0.14
    iani
    0.14
     Jaw
    0.14
    ä»ĭ
    0.13
    Act Density 0.479%

    No Known Activations