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

    Neuronpedia

    INDEX
    Explanations

    information or data presented with attribution to a source

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "according to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eg
    -0.80
    obyl
    -0.66
    affe
    -0.66
    otin
    -0.64
    riage
    -0.61
    ²¾
    -0.57
    ocker
    -0.56
    âĻ¦
    -0.55
    crow
    -0.54
    oiler
    -0.54
    POSITIVE LOGITS
    ãģĨ
    0.69
     sources
    0.65
    SOURCE
    0.64
     Reuters
    0.62
    thumbnails
    0.61
    taboola
    0.61
     to
    0.60
    patrick
    0.59
    graded
    0.59
     thereto
    0.58
    Act Density 0.048%

    No Known Activations