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

    Neuronpedia

    INDEX
    Explanations

    passes of time or transitions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conclusions or transitions in thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favourites
    -0.66
     favoured
    -0.63
     recognised
    -0.63
    iste
    -0.62
    orld
    -0.62
    lon
    -0.61
     condemned
    -0.61
     gravy
    -0.60
    bow
    -0.58
     recognized
    -0.57
    POSITIVE LOGITS
     Aires
    0.84
    ·
    0.84
     Mahjong
    0.80
    aucus
    0.75
     GOODMAN
    0.72
    Db
    0.71
    hift
    0.69
     Sachs
    0.64
     Ridley
    0.63
    ð
    0.63
    Act Density 0.170%

    No Known Activations