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

    Neuronpedia

    INDEX
    Explanations

    words related to entrepreneurial activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word 'surprising' or its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sub
    -0.64
     schedule
    -0.63
     ward
    -0.61
     autos
    -0.61
     frames
    -0.61
     baggage
    -0.60
     materials
    -0.58
     alcohol
    -0.57
     weights
    -0.57
     Diagn
    -0.57
    POSITIVE LOGITS
    prising
    4.54
    prise
    3.16
    prises
    3.13
    prisingly
    1.73
    tainment
    1.47
    pr
    1.21
    taining
    1.01
    pert
    0.95
    nexpected
    0.91
    plex
    0.90
    Act Density 0.026%

    No Known Activations