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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to change and transformation

    oai_token-act-pair · gpt-3.5-turbo

    significant changes and events in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imar
    -0.61
    ynski
    -0.59
    avis
    -0.58
     Waste
    -0.57
    arta
    -0.54
    ino
    -0.54
    oca
    -0.53
     recent
    -0.51
    icio
    -0.50
     upbringing
    -0.50
    POSITIVE LOGITS
     again
    0.95
     anew
    0.91
     tremend
    0.90
    again
    0.84
    .","
    0.81
    MSN
    0.76
    !!!!
    0.75
    !!!
    0.74
    .:
    0.74
    !!!!!
    0.74
    Act Density 0.943%

    No Known Activations