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

    Neuronpedia

    INDEX
    Explanations

    phrases denoting arguments or explanations

    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
    thro
    -0.66
    WARD
    -0.62
    natureconservancy
    -0.61
    ctic
    -0.61
    "],"
    -0.61
     Personnel
    -0.61
    Tax
    -0.60
    Guard
    -0.60
    EMBER
    -0.58
    Bott
    -0.58
    POSITIVE LOGITS
    cher
    0.74
     culminated
    0.73
     fateful
    0.71
     lasted
    0.71
     includes
    0.67
     resulted
    0.66
    soever
    0.66
    chers
    0.65
     mattered
    0.64
    'll
    0.64
    Act Density 0.091%

    No Known Activations