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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "Hud", or potential typos like "Hud" instead of "had"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Ciudad."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #$
    -0.74
    xon
    -0.68
    borough
    -0.63
     Painter
    -0.62
    Constructed
    -0.59
    ppard
    -0.58
    going
    -0.55
    =-=-
    -0.55
     Turing
    -0.55
     Constantin
    -0.54
    POSITIVE LOGITS
    geon
    1.53
    geoning
    1.34
    imentary
    1.22
    apest
    1.17
    geons
    1.15
    iamond
    1.11
    ges
    1.10
    elta
    1.01
    ible
    1.00
    ged
    0.99
    Act Density 0.026%

    No Known Activations