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

    Neuronpedia

    INDEX
    Explanations

    commands or requests in sentences

    oai_token-act-pair · gpt-3.5-turbo

    commands or urgent requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unnecess
    -0.70
    AMP
    -0.66
    EStreamFrame
    -0.62
     impacting
    -0.62
    UGC
    -0.62
     effected
    -0.62
    umerable
    -0.60
     Unloaded
    -0.60
     determining
    -0.60
     unwittingly
    -0.60
    POSITIVE LOGITS
     yourselves
    0.80
    ogly
    0.76
    ings
    0.76
     thou
    0.76
    iful
    0.73
     ya
    0.73
    !"
    0.72
     me
    0.71
    !'"
    0.70
    able
    0.70
    Act Density 0.222%

    No Known Activations