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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different products and business activities

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their contextual uses in various statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.74
     oun
    -0.68
     looted
    -0.67
     ingested
    -0.67
     coh
    -0.66
     brut
    -0.65
     overlooked
    -0.65
     gobl
    -0.65
     healed
    -0.64
     purse
    -0.64
    POSITIVE LOGITS
    Reviewer
    0.79
     Examples
    0.78
     Therefore
    0.77
     Specifically
    0.76
     However
    0.76
     Additionally
    0.75
     Depending
    0.75
     Possible
    0.74
     Logged
    0.74
     Again
    0.73
    Act Density 0.189%

    No Known Activations