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

    Neuronpedia

    INDEX
    Explanations

    words related to addresses and locations

    oai_token-act-pair · gpt-3.5-turbo

    significant nouns and phrases related to transactions, measurements, or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     festive
    -0.61
     Guth
    -0.60
     Pic
    -0.60
    joy
    -0.57
     snaps
    -0.56
     medals
    -0.56
    Spoiler
    -0.56
     Pulitzer
    -0.54
    wealth
    -0.54
    ++++++++++++++++
    -0.53
    POSITIVE LOGITS
    arte
    0.74
     nonetheless
    0.68
     thereafter
    0.66
    alion
    0.66
     targ
    0.66
     hers
    0.65
     preceded
    0.63
     yours
    0.63
     ours
    0.62
    IU
    0.62
    Act Density 0.715%

    No Known Activations