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

    Neuronpedia

    INDEX
    Explanations

    references to historical dates or events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    eye
    -0.76
    reet
    -0.73
    alion
    -0.67
    mare
    -0.66
    ucky
    -0.66
    allah
    -0.66
    osta
    -0.65
    iazep
    -0.64
    hold
    -0.64
    olas
    -0.64
    POSITIVE LOGITS
     Dating
    0.81
     antiquity
    0.68
     dating
    0.68
     Origins
    0.66
    Ancient
    0.64
     Reconstruction
    0.63
    ASED
    0.62
     prehistoric
    0.61
    dating
    0.61
    ocide
    0.61
    Act Density 0.012%

    No Known Activations