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

    Neuronpedia

    INDEX
    Explanations

    information related to specific numerical figures

    oai_token-act-pair · gpt-3.5-turbo

    significant data trends and patterns over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thirst
    -0.55
    minecraft
    -0.52
    lihood
    -0.50
     tray
    -0.50
     buttons
    -0.49
     pans
    -0.48
     clipboard
    -0.48
     Minion
    -0.47
    craft
    -0.47
    vec
    -0.46
    POSITIVE LOGITS
    bernatorial
    0.69
     revised
    0.65
    imester
    0.63
    cember
    0.60
     Reincarn
    0.58
     onwards
    0.57
    ategory
    0.55
    arij
    0.54
     coincide
    0.52
     coincided
    0.51
    Act Density 1.597%

    No Known Activations