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

    Neuronpedia

    INDEX
    Explanations

    words related to constraints, restrictions, or limitations

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "constant" and related forms or mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gestation
    -0.65
    mith
    -0.65
     Bohem
    -0.64
    cules
    -0.61
    kas
    -0.60
    ously
    -0.60
    TPS
    -0.59
    chy
    -0.59
     Bunny
    -0.58
     nerv
    -0.58
    POSITIVE LOGITS
    ellation
    1.63
    ipation
    1.49
    itution
    1.44
    abulary
    1.43
    itu
    1.41
    ruction
    1.39
    ricted
    1.39
    ricting
    1.34
    riction
    1.32
    rict
    1.32
    Act Density 0.029%

    No Known Activations