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

    Neuronpedia

    INDEX
    Explanations

    questions or conditional statements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ninger
    -0.15
     Wick
    -0.15
    eneg
    -0.14
    žel
    -0.14
    uden
    -0.14
     boz
    -0.14
    cai
    -0.13
    åľ¨çº¿è§Ĩé¢ij
    -0.13
    alous
    -0.13
     Uns
    -0.13
    POSITIVE LOGITS
    .sax
    0.16
    fab
    0.14
    çIJĨ
    0.14
    ever
    0.14
    ê¹
    0.14
    obi
    0.14
    een
    0.14
    ab
    0.13
    anton
    0.13
    affer
    0.13
    Act Density 0.044%

    No Known Activations