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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences indicating anticipation or warning of future events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating predictions or expectations about future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongh
    -0.70
     IPM
    -0.66
     prism
    -0.65
     resear
    -0.64
    tein
    -0.61
    rylic
    -0.60
     emphasizes
    -0.59
     emphasized
    -0.57
     quotas
    -0.57
     expertise
    -0.57
    POSITIVE LOGITS
     await
    1.28
     awaits
    1.20
     awaited
    1.14
     arise
    1.13
     happen
    1.12
    fall
    1.10
     ensued
    1.07
     unfold
    1.07
     Ahead
    1.06
     happens
    1.05
    Act Density 0.360%

    No Known Activations