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

    Neuronpedia

    INDEX
    Explanations

    commonly used terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms that indicate frequency of use or commonality in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hurry
    -0.77
    erity
    -0.74
     Awakens
    -0.73
     Wish
    -0.65
     Dragonbound
    -0.64
     deadlines
    -0.64
     haste
    -0.64
     Integrity
    -0.60
     deadline
    -0.60
    ourage
    -0.59
    POSITIVE LOGITS
     regarded
    1.37
     referred
    1.34
     seen
    1.31
     viewed
    1.27
     considered
    1.24
     categorized
    1.21
     associated
    1.20
     portrayed
    1.20
     depicted
    1.19
     used
    1.18
    Act Density 0.293%

    No Known Activations