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

    Neuronpedia

    INDEX
    Explanations

    phrases related to duration or time frames

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "quite."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ults
    -0.65
     DRAG
    -0.63
    osal
    -0.62
    olen
    -0.62
    otti
    -0.61
    ULTS
    -0.60
    venant
    -0.60
    angan
    -0.59
    ":"/
    -0.58
    kas
    -0.58
    POSITIVE LOGITS
     frankly
    1.11
     awhile
    0.88
     literally
    0.86
     rightly
    0.83
     possibly
    0.80
     honestly
    0.79
    entimes
    0.78
     alot
    0.78
    some
    0.77
     understandably
    0.75
    Act Density 0.020%

    No Known Activations