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

    Neuronpedia

    INDEX
    Explanations

    the concept of abstract ideas or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    references to concepts or ideas that are described as "notions."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aza
    -0.67
    aba
    -0.65
    GH
    -0.63
     each
    -0.61
    ests
    -0.61
    face
    -0.61
    borough
    -0.59
    chi
    -0.59
    xx
    -0.59
    SU
    -0.59
    POSITIVE LOGITS
     notion
    3.29
     idea
    2.25
     notions
    2.21
     concept
    1.81
     premise
    1.57
     proposition
    1.48
     assumption
    1.43
     conception
    1.41
     suggestion
    1.35
     misconception
    1.33
    Act Density 0.010%

    No Known Activations