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

    Neuronpedia

    INDEX
    Explanations

    information about criminal activities or accidents

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nah
    -0.73
    hare
    -0.70
    abs
    -0.67
    istant
    -0.66
    Being
    -0.64
    anguage
    -0.64
    lux
    -0.61
    bern
    -0.60
     guessing
    -0.60
    SPA
    -0.59
    POSITIVE LOGITS
     culminated
    1.63
     resulted
    1.62
     lasted
    1.49
     occurred
    1.36
     ended
    1.34
     ensued
    1.28
     led
    1.28
     preceded
    1.27
     yielded
    1.26
     prompted
    1.26
    Act Density 0.162%

    No Known Activations