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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'bold' in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bold" used to describe significant actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTOS
    -0.70
     Cheong
    -0.70
     duly
    -0.67
    enfranch
    -0.61
     Surv
    -0.59
     patiently
    -0.58
    ruciating
    -0.58
     Bulletin
    -0.57
     Dise
    -0.57
     Warfare
    -0.57
    POSITIVE LOGITS
    faced
    1.35
    face
    1.21
    er
    1.17
    ness
    1.14
    est
    1.05
    mouth
    0.96
    card
    0.90
    ened
    0.84
    nesses
    0.81
    eyed
    0.81
    Act Density 0.042%

    No Known Activations