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

    Neuronpedia

    INDEX
    Explanations

    phrases related to storytelling and character descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acho
    -0.14
    xico
    -0.14
    ure
    -0.14
     Ell
    -0.14
     Mey
    -0.13
     rhyme
    -0.13
     Rh
    -0.13
    isas
    -0.13
    arin
    -0.13
    kont
    -0.13
    POSITIVE LOGITS
     Kin
    0.19
    Kin
    0.19
     gal
    0.17
     Flint
    0.17
     Tone
    0.17
    gal
    0.17
    عا
    0.15
    Creator
    0.15
     naw
    0.15
     Bol
    0.15
    Act Density 0.001%

    No Known Activations