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

    Neuronpedia

    INDEX
    Explanations

    words related to various objects and activities

    oai_token-act-pair · gpt-3.5-turbo

    nouns and terms related to various forms of transportation and objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nightmares
    -0.64
     Origins
    -0.60
    League
    -0.59
     Bulldogs
    -0.59
    Prosecut
    -0.57
    oÄŁ
    -0.57
    SOURCE
    -0.57
     Bulgar
    -0.56
    Delivery
    -0.56
    Ī
    -0.54
    POSITIVE LOGITS
    mith
    1.44
    pace
    1.27
    peed
    1.22
    pring
    1.14
    paces
    1.13
    uggest
    1.13
    hift
    1.13
    poon
    1.12
    hip
    1.11
    poons
    1.10
    Act Density 0.669%

    No Known Activations