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

    Neuronpedia

    INDEX
    Explanations

    specific details or instances mentioned in a document

    oai_token-act-pair · gpt-3.5-turbo

    the word "specific" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĺħ
    -0.74
    ublic
    -0.73
     Alive
    -0.72
     Feldman
    -0.68
    frog
    -0.68
    ©¶æ
    -0.68
    ceans
    -0.67
    adays
    -0.66
    udder
    -0.65
    Wide
    -0.64
    POSITIVE LOGITS
    ities
    1.23
    ties
    1.01
     embodiments
    0.98
    ivity
    0.96
     identifiable
    0.94
    iating
    0.91
    iations
    0.87
    iveness
    0.86
    ity
    0.86
     kinds
    0.85
    Act Density 0.043%

    No Known Activations