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

    Neuronpedia

    INDEX
    Explanations

    parentheses and their associated content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idos
    -0.15
    ãģ¼
    -0.14
    ira
    -0.14
    ints
    -0.14
    æģ¯
    -0.14
    irling
    -0.14
    enas
    -0.13
    epam
    -0.13
    ikan
    -0.13
    ombat
    -0.13
    POSITIVE LOGITS
    aka
    0.19
     aka
    0.18
    fila
    0.16
     Shock
    0.15
    å¹¹
    0.15
     altern
    0.15
    skyt
    0.14
    ches
    0.14
    atz
    0.14
     Als
    0.14
    Act Density 0.215%

    No Known Activations