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

    Neuronpedia

    INDEX
    Explanations

    dates and events

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant events or actions being reported

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inav
    -0.77
    ILE
    -0.61
     subset
    -0.61
    must
    -0.61
     envy
    -0.58
    âĺ
    -0.58
     astronomy
    -0.57
    anto
    -0.57
     sums
    -0.57
     retains
    -0.56
    POSITIVE LOGITS
     aired
    0.94
     finalized
    0.93
     circulated
    0.91
     underway
    0.91
     released
    0.87
     happening
    0.86
     presented
    0.83
     publicized
    0.83
     implemented
    0.81
     unveiled
    0.80
    Act Density 0.319%

    No Known Activations