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

    Neuronpedia

    INDEX
    Explanations

    statistical values and medical information

    oai_token-act-pair · gpt-3.5-turbo

    statistical data and comparisons in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ounge
    -0.76
    terday
    -0.71
    Revolution
    -0.70
    aturday
    -0.69
    krit
    -0.68
    ulhu
    -0.68
    lah
    -0.67
    arcity
    -0.67
    ihad
    -0.66
    atche
    -0.66
    POSITIVE LOGITS
     âĪ¼
    1.12
     âĪĴ
    0.98
     âī¥
    0.92
    âĢIJ
    0.92
    )].
    0.88
     âī
    0.85
     β
    0.85
     ).
    0.84
     hypothesized
    0.84
     âī¤
    0.84
    Act Density 0.195%

    No Known Activations