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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing different types of emphasis and excitement in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ügen
    -0.18
    isay
    -0.16
    nip
    -0.16
    oins
    -0.16
    igate
    -0.15
    lify
    -0.15
    accumulate
    -0.15
    imore
    -0.15
    istar
    -0.15
    Enlarge
    -0.15
    POSITIVE LOGITS
     don
    0.23
    wik
    0.18
     rank
    0.17
     Perr
    0.17
    Don
    0.17
    don
    0.16
     try
    0.16
     limit
    0.15
     Don
    0.15
     arm
    0.15
    Act Density 0.355%

    No Known Activations