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

    Neuronpedia

    INDEX
    Explanations

    the presence of contributors and narrators in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Untitled
    -0.15
    ouble
    -0.15
    orre
    -0.14
    iaÅĤa
    -0.14
     Berm
    -0.14
    -sheet
    -0.14
    ahat
    -0.14
    км
    -0.14
    urette
    -0.14
    .compose
    -0.13
    POSITIVE LOGITS
    Narrated
    0.26
     narr
    0.22
     Narr
    0.20
     narrator
    0.20
     audi
    0.18
     Audi
    0.17
    Narr
    0.16
    asher
    0.16
    audi
    0.15
    lim
    0.15
    Act Density 0.004%

    No Known Activations