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

    Neuronpedia

    INDEX
    Explanations

    references to experiences and events that indicate significant changes or realizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prox
    -0.16
    integral
    -0.15
     outstanding
    -0.14
    obraz
    -0.14
    /theme
    -0.14
    inform
    -0.14
    CellValue
    -0.13
    義
    -0.13
    il
    -0.13
    æģ¯
    -0.13
    POSITIVE LOGITS
    ãĥĥãĥī
    0.15
     déjÃł
    0.15
     Anth
    0.14
    ams
    0.14
    LOAT
    0.14
    eza
    0.14
     Passport
    0.14
    gia
    0.13
     economies
    0.13
    909
    0.13
    Act Density 0.057%

    No Known Activations