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

    Neuronpedia

    INDEX
    Explanations

    references to fans and their interactions with various media content

    oai_token-act-pair · gpt-3.5-turbo

    references to fans and their engagement with productions or creators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.66
     Governor
    -0.62
     Morning
    -0.61
    innon
    -0.61
     Territ
    -0.59
     Labrador
    -0.59
    abus
    -0.59
     Khe
    -0.59
     Sheen
    -0.58
     Morph
    -0.57
    POSITIVE LOGITS
    atical
    1.14
    atics
    1.12
    erv
    1.10
    hip
    1.07
    ubs
    1.06
    haw
    1.05
    hips
    0.99
    atically
    0.96
    boys
    0.95
    hetical
    0.92
    Act Density 0.034%

    No Known Activations