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

    Neuronpedia

    INDEX
    Explanations

    references to famous literary characters and authors

    oai_token-act-pair · gpt-3.5-turbo

    references to the character Sherlock Holmes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ktop
    -0.79
    grading
    -0.74
    graded
    -0.71
    semble
    -0.71
    pleting
    -0.70
    lag
    -0.69
    vg
    -0.66
    auri
    -0.65
    onies
    -0.65
    isconsin
    -0.64
    POSITIVE LOGITS
     Holmes
    1.42
     Sherlock
    1.21
    Lens
    0.89
     Cumber
    0.85
    batch
    0.79
     Doyle
    0.78
     Lect
    0.74
     Clara
    0.73
    âĸĪâĸĪâĸĪâĸĪ
    0.73
    ©¶æ¥µ
    0.73
    Act Density 0.011%

    No Known Activations