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

    Neuronpedia

    INDEX
    Explanations

    mentions of the letter 'Q' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the letter 'Q' followed by a number, likely related to quarterly data or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fulness
    -0.84
     Awakens
    -0.76
    ufact
    -0.74
    wagen
    -0.74
     Lauder
    -0.74
    éĹĺ
    -0.72
     Nadu
    -0.67
    coni
    -0.66
    milo
    -0.65
     fullest
    -0.63
    POSITIVE LOGITS
    WER
    0.97
    atari
    0.93
    UE
    0.92
    addafi
    0.91
    ued
    0.87
    ues
    0.85
    agan
    0.85
    atana
    0.84
    atar
    0.84
    aida
    0.81
    Act Density 0.020%

    No Known Activations