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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accumulation or adding up of things

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating accumulation or summation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Colonial
    -0.62
    ãĥĨ
    -0.61
     Dawn
    -0.61
     proclamation
    -0.58
    bies
    -0.58
     Jed
    -0.58
    ials
    -0.58
    gow
    -0.57
     Lazarus
    -0.56
     Jude
    -0.56
    POSITIVE LOGITS
     nicely
    1.02
     differently
    0.95
     vividly
    0.88
     neatly
    0.82
     horribly
    0.82
     smoothly
    0.81
     unpredict
    0.80
     smoother
    0.76
     beautifully
    0.75
     logically
    0.74
    Act Density 0.154%

    No Known Activations