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

    Neuronpedia

    INDEX
    Explanations

    words related to medical procedures or scientific figures

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific symbols or characters that seem irregular or non-standard in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     metic
    -0.99
     CAS
    -0.78
     ANGEL
    -0.77
     SUN
    -0.75
     SIM
    -0.73
     CY
    -0.73
     AS
    -0.73
     ROS
    -0.72
     JPM
    -0.71
     COM
    -0.70
    POSITIVE LOGITS
    c
    1.74
    d
    1.67
    b
    1.66
    h
    1.62
    p
    1.62
    r
    1.59
    f
    1.58
    e
    1.55
    sb
    1.53
    t
    1.50
    Act Density 0.195%

    No Known Activations