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

    Neuronpedia

    INDEX
    Explanations

    the repetition of the syllable "um" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Houſe
    -1.20
     queſta
    -1.13
     myſelf
    -1.09
     houſe
    -1.06
     Reſ
    -1.02
     itſelf
    -1.01
    parsedMessage
    -0.98
     Anſ
    -0.98
     faſt
    -0.98
     pleaſure
    -0.95
    POSITIVE LOGITS
    um
    1.00
    up
    0.75
    UM
    0.75
    er
    0.69
    ett
    0.69
    uch
    0.65
     wild
    0.65
    ung
    0.60
    ert
    0.60
    ug
    0.59
    Act Density 0.537%

    No Known Activations