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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences indicating agreement or acceptance

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the word "Okay"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     brim
    -0.77
    advert
    -0.69
    pent
    -0.68
    effic
    -0.67
    expression
    -0.67
    bath
    -0.65
    eatured
    -0.65
    minecraft
    -0.64
    clipse
    -0.63
    annot
    -0.62
    POSITIVE LOGITS
    lahoma
    1.17
     bye
    0.97
    Okay
    0.89
    AY
    0.85
     Alright
    0.77
    Alright
    0.76
    oka
    0.74
     Okay
    0.74
     okay
    0.72
     Cancel
    0.71
    Act Density 0.019%

    No Known Activations