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

    Neuronpedia

    INDEX
    Explanations

    certain types of suffixes or prefixes commonly found in words related to policy and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    den
    -0.16
    iqueta
    -0.14
    Ĵáŀ
    -0.14
    ASCADE
    -0.14
    LOCKS
    -0.14
    IColor
    -0.14
    arra
    -0.14
    Ú¯ÙĦ
    -0.13
    dana
    -0.13
    olis
    -0.13
    POSITIVE LOGITS
     Tucker
    0.16
    ucci
    0.16
    ervlet
    0.14
    à¸²à¸ł
    0.14
     Boo
    0.14
    orida
    0.13
    оÑī
    0.13
     Tick
    0.13
    ovali
    0.13
    emes
    0.13
    Act Density 0.124%

    No Known Activations