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

    Neuronpedia

    INDEX
    Explanations

    slashes followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    slashes and various formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pepsi
    -0.72
     Moody
    -0.71
     MacArthur
    -0.69
     Wasserman
    -0.69
     expans
    -0.69
     tender
    -0.68
     narrowly
    -0.67
     lapse
    -0.66
     right
    -0.64
     Cantor
    -0.64
    POSITIVE LOGITS
    \/\/
    1.42
    usr
    1.25
    ********************************
    1.15
    ËĪ
    1.13
    uploads
    1.07
    Users
    1.03
    Film
    1.02
    pol
    1.01
    etc
    1.01
    gallery
    0.99
    Act Density 0.023%

    No Known Activations