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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Acc" consistently followed by a number which implies some sort of accreditation or official recognition

    oai_token-act-pair · gpt-3.5-turbo

    references to accreditation or standards related to safety and industry practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPLE
    -0.84
    geist
    -0.82
    NING
    -0.69
    berman
    -0.69
     Dare
    -0.67
    bian
    -0.67
    wich
    -0.65
    enegger
    -0.65
     hope
    -0.64
    lyak
    -0.64
    POSITIVE LOGITS
    redited
    1.22
    enture
    1.18
    identally
    1.17
    ompl
    1.16
    used
    1.12
    reditation
    1.11
    ommod
    1.10
    idental
    1.10
    urate
    1.06
    iona
    1.05
    Act Density 0.009%

    No Known Activations