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

    Neuronpedia

    INDEX
    Explanations

    references to films and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     grace
    -0.18
    ipp
    -0.16
     Grace
    -0.15
     Boeh
    -0.15
    395
    -0.14
     Dro
    -0.14
     Bros
    -0.14
    hta
    -0.14
    -0.14
    hton
    -0.14
    POSITIVE LOGITS
    contres
    0.20
    DSL
    0.15
    jal
    0.15
    ARAM
    0.15
    vise
    0.14
    ioc
    0.14
     ninete
    0.14
    ALAR
    0.14
     вк
    0.14
    PTY
    0.14
    Act Density 0.027%

    No Known Activations