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

    Neuronpedia

    INDEX
    Explanations

    words related to the term "sum"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "um" indicating hesitation or filler speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffff
    -0.71
     strawberries
    -0.71
     blackout
    -0.69
     resemb
    -0.66
     unaff
    -0.64
    jri
    -0.64
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.63
     straw
    -0.59
     fatty
    -0.58
    ¬¼
    -0.57
    POSITIVE LOGITS
    mers
    1.18
    ming
    1.10
    pty
    1.02
    mit
    0.95
    mate
    0.93
    mary
    0.92
    essage
    0.86
    etric
    0.85
    atism
    0.84
    antic
    0.84
    Act Density 0.030%

    No Known Activations