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

    Neuronpedia

    INDEX
    Explanations

    instances of the preposition 'on' followed by a location or activity

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INESS
    -0.66
    ι
    -0.63
    acter
    -0.61
    Cat
    -0.61
    ãĤ¼ãĤ¦ãĤ¹
    -0.61
    rament
    -0.61
    ptive
    -0.60
    rieg
    -0.57
    TextColor
    -0.57
    imilation
    -0.56
    POSITIVE LOGITS
     behalf
    1.43
     occasion
    1.09
    etime
    1.07
    coming
    1.04
    screen
    1.04
    shore
    0.91
    eday
    0.90
    eness
    0.90
    demand
    0.90
     steroids
    0.89
    Act Density 0.290%

    No Known Activations