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

    Neuronpedia

    INDEX
    Explanations

    years expressed as numbers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    achus
    -0.78
     akin
    -0.67
    chy
    -0.62
     helicop
    -0.59
     torches
    -0.58
    ufficient
    -0.57
    peak
    -0.57
     lobb
    -0.56
    atively
    -0.56
    apps
    -0.56
    POSITIVE LOGITS
     olds
    1.11
     ago
    0.96
     old
    0.93
     anniversary
    0.89
    old
    0.87
    olds
    0.82
     Ago
    0.78
    iversary
    0.77
    OLD
    0.73
     Anniversary
    0.72
    Act Density 0.238%

    No Known Activations