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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating location or direction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "one of" indicating examples or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lees
    -0.77
    ans
    -0.70
    anse
    -0.66
    ption
    -0.65
    body
    -0.65
    etermination
    -0.64
    matter
    -0.62
     disadvant
    -0.60
    leans
    -0.60
    ening
    -0.59
    POSITIVE LOGITS
     these
    0.77
     Europe
    0.76
     those
    0.75
     three
    0.75
     our
    0.74
     Britain
    0.74
     two
    0.72
     America
    0.72
     my
    0.71
     innumerable
    0.70
    Act Density 0.071%

    No Known Activations