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

    Neuronpedia

    INDEX
    Explanations

    references to visual media and the act of watching films or shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zell
    -0.17
    legg
    -0.15
    Visibility
    -0.15
    lector
    -0.15
     anonymity
    -0.14
    UPI
    -0.14
    /Public
    -0.14
    Ãło
    -0.14
    ró
    -0.14
    quires
    -0.14
    POSITIVE LOGITS
     cover
    0.22
     aloud
    0.21
     relig
    0.19
     unfold
    0.19
     religious
    0.19
     forwards
    0.18
     backwards
    0.18
     backward
    0.18
    /watch
    0.18
     attent
    0.18
    Act Density 0.152%

    No Known Activations