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

    Neuronpedia

    INDEX
    Explanations

    specific phrases with the presence of the word "of" followed by a subsequent focus word indicating a key piece of information or object

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to specific types of information or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcs
    -0.73
    WT
    -0.66
    bia
    -0.65
    DOS
    -0.64
    reys
    -0.64
    rise
    -0.64
    channelAvailability
    -0.62
    qq
    -0.61
    gyn
    -0.61
    ARS
    -0.60
    POSITIVE LOGITS
     liner
    0.75
     cake
    0.68
    icial
    0.63
     mosaic
    0.62
    axy
    0.62
     Savior
    0.61
     blocks
    0.61
     armor
    0.61
     polish
    0.60
     silver
    0.59
    Act Density 0.110%

    No Known Activations