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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating size, quality, or specifics of substances and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     instance
    -0.15
     thing
    -0.15
    iej
    -0.14
    UBLE
    -0.14
    iente
    -0.14
    omaly
    -0.14
    olate
    -0.14
    aday
    -0.14
    ffects
    -0.14
    ÑĩиÑģл
    -0.14
    POSITIVE LOGITS
     vengeance
    0.34
     emphasis
    0.32
     twist
    0.28
     Twist
    0.28
     focus
    0.27
     regards
    0.25
    bang
    0.24
     bang
    0.23
     regard
    0.23
    emphasis
    0.23
    Act Density 0.103%

    No Known Activations