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

    Neuronpedia

    INDEX
    Explanations

    dialogue that includes emotional or tense interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erti
    -0.16
    alars
    -0.16
    ogan
    -0.15
    owi
    -0.15
    oga
    -0.15
    porno
    -0.14
     dna
    -0.14
     karak
    -0.14
    esis
    -0.14
    lemen
    -0.14
    POSITIVE LOGITS
    BX
    0.14
    asel
    0.14
    cko
    0.14
    .Glide
    0.13
    od
    0.13
    kh
    0.13
    781
    0.12
     Airlines
    0.12
    mare
    0.12
    _browser
    0.12
    Act Density 1.872%

    No Known Activations