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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating some sort of citation or quote

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their associated significance in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     https
    -0.66
     Travis
    -0.63
     Thomas
    -0.61
     http
    -0.59
     Hamilton
    -0.59
     Couch
    -0.58
     pic
    -0.57
     HT
    -0.57
     Bengals
    -0.56
     Vit
    -0.56
    POSITIVE LOGITS
    ".[
    3.94
    ."[
    3.86
    ).[
    2.66
    .[
    2.34
    "[
    2.28
    ,[
    2.12
    :[
    2.04
    )[
    1.82
    [/
    1.79
    !".
    1.58
    Act Density 0.010%

    No Known Activations