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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue and character interactions in film and literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lava
    -0.17
    atha
    -0.17
    argas
    -0.15
    argins
    -0.15
    ãĥªãĤ¹
    -0.15
    AMESPACE
    -0.15
    ousel
    -0.14
    erosis
    -0.14
    Streamer
    -0.14
    sÃŃ
    -0.14
    POSITIVE LOGITS
     dummy
    0.16
    ysa
    0.16
     actual
    0.15
     Safety
    0.15
     Authentic
    0.14
     Actual
    0.14
    ãĤº
    0.14
    iyan
    0.14
     Dummy
    0.13
     Wahl
    0.13
    Act Density 0.217%

    No Known Activations