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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people, places, and brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¬ģ
    -0.17
    ¬Ĥ
    -0.14
    osate
    -0.14
     Sinai
    -0.14
    shaled
    -0.13
    -aos
    -0.13
    .EntityFramework
    -0.13
    æ³³
    -0.13
    íĥģ
    -0.13
    #af
    -0.13
    POSITIVE LOGITS
    ett
    0.40
    itt
    0.38
    ott
    0.37
     ICC
    0.36
    OTT
    0.36
    utt
    0.36
    onn
    0.35
    oll
    0.35
    ITT
    0.35
     Orr
    0.34
    Act Density 0.575%

    No Known Activations