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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "though" is used in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    phrases or clauses that introduce contrasting or conditional ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ULAR
    -0.62
    SourceFile
    -0.59
    CLOSE
    -0.59
    Krist
    -0.58
     suitcase
    -0.57
    MJ
    -0.56
    mate
    -0.56
    cott
    -0.54
    om
    -0.54
    WD
    -0.53
    POSITIVE LOGITS
     alas
    0.74
     unlike
    0.69
    âķIJâķIJ
    0.68
    acha
    0.68
    ettings
    0.68
     anecd
    0.67
     nonetheless
    0.66
    artifacts
    0.66
     //[
    0.66
     beware
    0.65
    Act Density 0.086%

    No Known Activations