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

    Neuronpedia

    INDEX
    Explanations

    phrases prompting the reader to consider or examine something

    oai_token-act-pair · gpt-3.5-turbo

    imperative phrases that instruct or suggest actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     advertised
    -0.73
     embr
    -0.66
    etter
    -0.62
     constitu
    -0.61
    mith
    -0.61
    oline
    -0.60
    iege
    -0.60
    icol
    -0.60
     accompanies
    -0.59
    oad
    -0.59
    POSITIVE LOGITS
    aways
    1.45
    away
    1.14
    overs
    0.93
    uchi
    0.90
     aback
    0.86
     advantage
    0.85
     heed
    0.84
    prising
    0.75
    frey
    0.73
    rolet
    0.71
    Act Density 0.030%

    No Known Activations