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

    Neuronpedia

    INDEX
    Explanations

    numbers and references to competition results, events, and achievements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    aminer
    -0.71
    SHIP
    -0.67
    IDS
    -0.64
    assembly
    -0.59
    ritic
    -0.58
    potion
    -0.58
    rir
    -0.57
     Kamp
    -0.57
    yip
    -0.57
    ker
    -0.56
    POSITIVE LOGITS
    ocating
    1.40
    iances
    1.24
     kinds
    1.21
    igators
    1.20
     sorts
    1.17
    iance
    1.17
    igator
    1.17
    usions
    1.15
    ocated
    1.13
    uding
    1.12
    Act Density 1.580%

    No Known Activations