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

    Neuronpedia

    INDEX
    Explanations

    references originating or directing information to specific individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    iencies
    -0.85
    estyles
    -0.79
    merce
    -0.75
    few
    -0.74
    lied
    -0.74
    ikes
    -0.73
    selection
    -0.73
     pioneered
    -0.73
    wcsstore
    -0.71
    ãĤ¦ãĤ¹
    -0.71
    POSITIVE LOGITS
     superiors
    0.88
     afar
    0.84
     sender
    0.82
     whence
    0.81
     abroad
    0.76
     heaven
    0.75
     Cyrus
    0.73
     Burk
    0.67
     Papa
    0.67
     inside
    0.66
    Act Density 0.089%

    No Known Activations