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

    Neuronpedia

    INDEX
    Explanations

    exclamations and interjections

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abb
    -0.68
    orate
    -0.67
    copy
    -0.65
    edge
    -0.64
    ictions
    -0.64
    Central
    -0.61
    itations
    -0.61
    icip
    -0.60
    Hispanic
    -0.59
    atics
    -0.59
    POSITIVE LOGITS
     Oh
    3.31
     oh
    2.15
    Oh
    1.98
     Ah
    1.66
     Huh
    1.65
     Hey
    1.65
     Uh
    1.57
     Yeah
    1.49
     Wow
    1.46
     Okay
    1.44
    Act Density 0.010%

    No Known Activations