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

    Neuronpedia

    INDEX
    Explanations

    punctuations and symbols, possibly indicating narrative structure or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -,
    -0.17
    ","","
    -0.15
    aks
    -0.14
    989
    -0.14
    ãĢģäºĮ
    -0.14
    azz
    -0.14
    vault
    -0.14
     roller
    -0.14
     tern
    -0.14
    è¡Ĩ
    -0.14
    POSITIVE LOGITS
    ombat
    0.18
    mana
    0.17
     fitte
    0.16
    iram
    0.16
    erman
    0.16
    defgroup
    0.16
    ibold
    0.14
    mast
    0.14
    Viewport
    0.14
    ÃĹ↵↵
    0.14
    Act Density 0.100%

    No Known Activations