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

    Neuronpedia

    INDEX
    Explanations

    mentions of placing something in a specific position or state

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iffe
    -0.64
    !
    -0.64
    atio
    -0.61
    ature
    -0.61
    illon
    -0.60
    bg
    -0.60
    arry
    -0.60
    ornings
    -0.59
    cheon
    -0.58
    !!
    -0.58
    POSITIVE LOGITS
     same
    1.24
     slightest
    1.19
     entire
    1.18
     widest
    1.09
     latter
    1.08
     quickest
    1.07
    ses
    1.04
     biggest
    1.04
     greatest
    1.03
     whole
    1.03
    Act Density 0.418%

    No Known Activations