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

    Neuronpedia

    INDEX
    Explanations

    references to television series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    636
    -0.17
     Uhr
    -0.16
     Watkins
    -0.15
    dea
    -0.15
    odus
    -0.15
    zel
    -0.14
    zos
    -0.14
    odos
    -0.14
    sed
    -0.14
    ered
    -0.14
    POSITIVE LOGITS
     Hust
    0.16
    adele
    0.15
    agal
    0.15
    arih
    0.14
    Ļ
    0.14
    endl
    0.14
     blame
    0.14
    çģ
    0.13
    ampoo
    0.13
    imore
    0.13
    Act Density 0.010%

    No Known Activations