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

    Neuronpedia

    INDEX
    Explanations

    references to the position "slot receiver."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.67
    ĨĴ
    -0.66
    harm
    -0.66
    omorphic
    -0.63
    vironment
    -0.60
    kj
    -0.60
    ullivan
    -0.60
    ors
    -0.59
    issance
    -0.58
     Principles
    -0.57
    POSITIVE LOGITS
    ting
    1.22
    tery
    1.05
    ted
    0.90
    machine
    0.83
    ular
    0.82
    ioned
    0.81
     slots
    0.81
     slot
    0.80
    rette
    0.78
    lot
    0.78
    Act Density 0.018%

    No Known Activations