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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "On"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "On" followed by various contexts or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OULD
    -0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.66
    Ĥª
    -0.63
    ikan
    -0.59
    ILY
    -0.58
    ãĤ£
    -0.57
     DOI
    -0.57
     Slug
    -0.57
     Inquisition
    -0.57
    ãĤ©
    -0.56
    POSITIVE LOGITS
    coming
    1.37
    slaught
    1.21
    demand
    1.17
    etime
    1.12
    eday
    1.12
    yx
    1.10
    shore
    1.08
     behalf
    1.04
    eness
    1.02
    slow
    1.02
    Act Density 0.116%

    No Known Activations