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

    Neuronpedia

    INDEX
    Explanations

    references to popular television series and their characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¦ĸ
    -0.17
    thora
    -0.16
    ccoli
    -0.15
     Annunci
    -0.14
     Macron
    -0.14
    ÑģÑĤа
    -0.14
    ken
    -0.14
     maç
    -0.14
     Penalty
    -0.14
    ÑĢоÑĦ
    -0.14
    POSITIVE LOGITS
     meth
    0.31
     Walt
    0.30
     Breaking
    0.28
     Walter
    0.28
    meth
    0.27
    Breaking
    0.26
     Albuquerque
    0.24
     Jesse
    0.24
     Meth
    0.23
     Gale
    0.23
    Act Density 0.003%

    No Known Activations