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

    Neuronpedia

    INDEX
    Explanations

    instances of conversational phrases or filler words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     @"/
    -0.75
    knapp
    -0.63
     lunghi
    -0.61
    bitat
    -0.60
    ishments
    -0.60
     Krav
    -0.60
    EnableWeb
    -0.59
    XmlAccessType
    -0.59
    ankind
    -0.59
    ventura
    -0.59
    POSITIVE LOGITS
     sees
    1.17
     see
    1.13
     saw
    1.07
     Sees
    1.06
     seen
    1.05
     SEE
    1.03
    see
    0.97
    saw
    0.97
     SEEN
    0.96
     seeing
    0.96
    Act Density 0.064%

    No Known Activations