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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency or common occurrence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize frequency or habitual actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.72
    anth
    -0.70
     Achievement
    -0.70
    vich
    -0.69
    otiation
    -0.68
    ajor
    -0.68
    sure
    -0.67
    atis
    -0.67
    ocracy
    -0.67
    atsu
    -0.67
    POSITIVE LOGITS
    entimes
    1.62
     overlooked
    1.32
     times
    1.23
    times
    1.22
     misunderstood
    1.09
     mistaken
    1.07
     referred
    1.06
     errone
    1.03
     mistakenly
    1.01
     underestimated
    1.00
    Act Density 0.058%

    No Known Activations