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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant actions or events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    icion
    -0.71
    lav
    -0.70
    SHIP
    -0.69
    yip
    -0.65
     Chambers
    -0.62
    column
    -0.61
    VERTISEMENT
    -0.61
    olate
    -0.60
     guiIcon
    -0.60
    ceiver
    -0.59
    POSITIVE LOGITS
    ocating
    1.03
    usions
    0.98
     else
    0.98
    uding
    0.97
     kinds
    0.96
     traces
    0.92
    igators
    0.92
    ude
    0.92
     sorts
    0.92
    owing
    0.90
    Act Density 0.064%

    No Known Activations