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

    Neuronpedia

    INDEX
    Explanations

    people or groups followed by actions or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or individuals defined by the word "who"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fresh
    -0.64
     Shake
    -0.63
    >>>>>>>>
    -0.63
     Birds
    -0.59
    LAN
    -0.59
    fresh
    -0.58
    hander
    -0.58
     drying
    -0.56
    Fresh
    -0.56
     Craw
    -0.56
    POSITIVE LOGITS
     oppose
    1.03
     partake
    0.95
     criticize
    0.94
     benefited
    0.93
     succeed
    0.92
     prevail
    0.88
     survived
    0.87
     specialize
    0.87
     argue
    0.85
     perished
    0.84
    Act Density 0.130%

    No Known Activations