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

    Neuronpedia

    INDEX
    Explanations

    sentence endings

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.66
     abduct
    -0.64
     hatch
    -0.64
     axe
    -0.63
     affili
    -0.62
     ogre
    -0.59
     uncom
    -0.59
     purse
    -0.58
     mur
    -0.58
    ascus
    -0.57
    POSITIVE LOGITS
     However
    1.13
     Though
    1.13
     Although
    1.06
     Nevertheless
    1.04
     Whereas
    1.04
     Additionally
    1.03
     Instead
    1.02
     While
    1.02
     Whether
    1.01
     Nonetheless
    1.01
    Act Density 0.852%

    No Known Activations