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

    Neuronpedia

    INDEX
    Explanations

    short phrases or sentences ending in a period or exclamation mark

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express opinions or judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inund
    -0.78
     credential
    -0.76
    ensable
    -0.71
     privileged
    -0.71
     illicit
    -0.69
    idal
    -0.69
    reet
    -0.69
     escape
    -0.68
     unsus
    -0.68
     unle
    -0.68
    POSITIVE LOGITS
     Anyway
    1.70
     Otherwise
    1.48
     Lastly
    1.46
     Also
    1.46
     Personally
    1.44
     Secondly
    1.43
     Hopefully
    1.43
     Regardless
    1.41
    Anyway
    1.40
     Especially
    1.36
    Act Density 0.493%

    No Known Activations