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

    Neuronpedia

    INDEX
    Explanations

    instances where one entity interacts with or refers to another entity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "other."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     1915
    -0.68
    aram
    -0.66
    terday
    -0.63
    _-
    -0.61
    theless
    -0.60
    anism
    -0.60
    veland
    -0.60
    zon
    -0.59
    arella
    -0.59
     Retrieved
    -0.58
    POSITIVE LOGITS
    worldly
    1.78
     side
    0.96
     senses
    0.78
    parts
    0.76
    world
    0.74
     thing
    0.74
     aspects
    0.73
     guy
    0.73
    quickShipAvailable
    0.72
    swer
    0.71
    Act Density 0.042%

    No Known Activations