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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that end in a period

    oai_token-act-pair · gpt-3.5-turbo

    conclusions or statements at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dimensional
    -0.82
     skelet
    -0.80
     strap
    -0.77
     overshadow
    -0.75
     compliment
    -0.74
    mble
    -0.73
    plet
    -0.73
    oward
    -0.73
    erest
    -0.72
    marine
    -0.72
    POSITIVE LOGITS
     Typically
    1.32
     Therefore
    1.25
     Applic
    1.25
     Generally
    1.24
     Usually
    1.23
     Normally
    1.23
     Individuals
    1.23
     Courts
    1.22
    Applic
    1.22
     Otherwise
    1.21
    Act Density 0.463%

    No Known Activations