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

    Neuronpedia

    INDEX
    Explanations

    conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "but" used to introduce contrasting statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itton
    -0.79
    oided
    -0.78
    IUM
    -0.75
    ais
    -0.75
    LI
    -0.75
    tnc
    -0.74
    john
    -0.73
    oun
    -0.72
    ences
    -0.68
    Ohio
    -0.68
    POSITIVE LOGITS
     nor
    1.31
     anymore
    1.22
    chery
    0.86
     unless
    0.78
     except
    0.77
     yet
    0.75
     alas
    0.75
     merely
    0.73
     preferring
    0.73
     necessarily
    0.72
    Act Density 0.090%

    No Known Activations