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

    Neuronpedia

    INDEX
    Explanations

    battery sizes

    oai_token-act-pair · gpt-3.5-turbo

    references to battery types and credit ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dunham
    -0.80
    osuke
    -0.78
    stall
    -0.76
    ãĥĭ
    -0.75
    ners
    -0.73
     Osw
    -0.72
    former
    -0.71
    ãĥĪ
    -0.71
    sell
    -0.71
    rer
    -0.70
    POSITIVE LOGITS
    BIL
    0.84
    BA
    0.81
    ECA
    0.79
    ccording
    0.77
    IDE
    0.77
    enture
    0.76
    amily
    0.75
    HHHH
    0.75
    arbon
    0.74
    VERTISEMENT
    0.74
    Act Density 0.010%

    No Known Activations