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

    Neuronpedia

    INDEX
    Explanations

    examples of phrases indicating progress or advancement

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in the" along with incremental mentions of "step."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chell
    -0.63
    ln
    -0.59
     %%
    -0.58
    nces
    -0.58
    lynn
    -0.58
    llor
    -0.58
    ractive
    -0.57
     heirs
    -0.57
    ãĥĻ
    -0.56
     ported
    -0.56
    POSITIVE LOGITS
    efficiency
    1.24
    humane
    1.16
    effic
    1.07
    ordinate
    1.06
     lieu
    1.04
     vitro
    1.00
    animate
    0.97
    clusions
    0.96
    escap
    0.95
    offensive
    0.94
    Act Density 0.206%

    No Known Activations