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

    Neuronpedia

    INDEX
    Explanations

    the number "Seven" mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    the repeated occurrence of the word "seven"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.72
    agate
    -0.69
    plom
    -0.65
    ller
    -0.64
     srf
    -0.63
    Document
    -0.61
     Cutter
    -0.61
     Palestin
    -0.61
    atum
    -0.58
    reference
    -0.58
    POSITIVE LOGITS
    teen
    1.36
    eenth
    1.32
    een
    1.30
    teenth
    1.28
     hundred
    1.10
    fold
    1.08
     months
    0.95
     thousand
    0.94
     weeks
    0.92
    fif
    0.91
    Act Density 0.029%

    No Known Activations