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

    Neuronpedia

    INDEX
    Explanations

    references to historical games and their thematic elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     brig
    -0.16
     paddle
    -0.15
    enza
    -0.15
    å¹²
    -0.14
    eat
    -0.14
     derec
    -0.14
    ité
    -0.13
     Patterson
    -0.13
    uced
    -0.13
    ,ev
    -0.13
    POSITIVE LOGITS
     Tau
    0.19
     Eisen
    0.18
     Lorem
    0.18
    hammer
    0.18
     Bolt
    0.18
     Nur
    0.16
    PIP
    0.16
    orgh
    0.16
     GW
    0.16
     Imperial
    0.15
    Act Density 0.017%

    No Known Activations