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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legislative actions and potential political movements

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iuses
    -0.68
    ¬¼
    -0.66
    rou
    -0.65
    opus
    -0.65
    sych
    -0.63
    inus
    -0.60
    Generic
    -0.60
    hero
    -0.60
    ounded
    -0.58
    aste
    -0.57
    POSITIVE LOGITS
     preferably
    1.28
     assuming
    1.11
     albeit
    1.08
     although
    1.04
     barring
    1.03
     regardless
    1.01
     depending
    1.00
     lest
    1.00
    assuming
    0.97
     unless
    0.96
    Act Density 0.344%

    No Known Activations