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

    Neuronpedia

    INDEX
    Explanations

    titles and names of films and television shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Occurs
    -0.15
     «
    -0.15
     or
    -0.14
     Bog
    -0.14
    ää
    -0.14
    ozo
    -0.14
    amura
    -0.14
     certainly
    -0.13
    erp
    -0.13
     fitting
    -0.13
    POSITIVE LOGITS
    rish
    0.15
    ucz
    0.15
    vents
    0.14
    illin
    0.14
    elden
    0.14
    orem
    0.14
    {%
    0.14
    unifu
    0.14
    uste
    0.14
    inerary
    0.13
    Act Density 0.231%

    No Known Activations