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

    Neuronpedia

    INDEX
    Explanations

    significant numbers and quantities

    oai_token-act-pair · gpt-3.5-turbo

    significant numerical values and related measurements in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NULL
    -0.75
    ebin
    -0.73
    ename
    -0.65
    Appearance
    -0.62
     srfAttach
    -0.62
    artifacts
    -0.59
     lieu
    -0.59
    wait
    -0.59
    ]=
    -0.59
     ç¥ŀ
    -0.58
    POSITIVE LOGITS
     seen
    1.11
     envisioned
    1.03
     touted
    0.98
     observed
    0.96
     contemplated
    0.95
     discussed
    0.95
     found
    0.94
     discovered
    0.93
     practiced
    0.93
     employed
    0.92
    Act Density 0.455%

    No Known Activations