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

    Neuronpedia

    INDEX
    Explanations

    words related to Sherlock Holmes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Holmes" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ital
    -0.79
    ribute
    -0.69
    inished
    -0.68
    resent
    -0.68
    semble
    -0.68
    ript
    -0.66
    iliated
    -0.66
    endants
    -0.65
    racted
    -0.63
    å§
    -0.63
    POSITIVE LOGITS
     Holmes
    1.28
    iday
    0.86
    Lens
    0.83
    worms
    0.74
     Weasley
    0.73
    combe
    0.72
     Hole
    0.72
     TAMADRA
    0.71
     Manor
    0.71
     Sherlock
    0.71
    Act Density 0.007%

    No Known Activations