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

    Neuronpedia

    INDEX
    Explanations

    places or locations

    oai_token-act-pair · gpt-3.5-turbo

    the presence of tokenized segments or special delimiters, indicating the end of textual segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.80
    jri
    -0.80
     disg
    -0.78
     pse
    -0.76
     agre
    -0.74
     compe
    -0.71
     UNCLASSIFIED
    -0.69
     challeng
    -0.69
    _.
    -0.68
     afterward
    -0.67
    POSITIVE LOGITS
     âĢº
    0.88
     Calculator
    0.82
     Profile
    0.79
     Brewing
    0.76
    Wiki
    0.73
     Originally
    0.70
    pedia
    0.69
     Quote
    0.67
     Tutorial
    0.65
     Posted
    0.64
    Act Density 0.597%

    No Known Activations