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

    Neuronpedia

    INDEX
    Explanations

    phrases related to competition and motivation

    oai_token-act-pair · gpt-3.5-turbo

    affirmations of belief and definitive statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ®
    -0.61
    ãĤ´ãĥ³
    -0.59
     Amid
    -0.55
     Alas
    -0.54
    arist
    -0.52
    NOW
    -0.52
    surprisingly
    -0.50
     Bare
    -0.50
    antic
    -0.49
     Yet
    -0.49
    POSITIVE LOGITS
     [
    0.94
    entimes
    0.82
     gonna
    0.80
    ,'"
    0.78
     everybody
    0.75
     mathemat
    0.75
     ..."
    0.75
    ),"
    0.74
    )."
    0.73
     âĢ¦"
    0.72
    Act Density 1.639%

    No Known Activations