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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with a specific punctuation mark

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with periods or denote completion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uer
    -0.88
     affili
    -0.76
     arra
    -0.76
     unequ
    -0.75
     occupation
    -0.75
     credential
    -0.74
     opponent
    -0.73
     earthqu
    -0.73
     heir
    -0.73
     temperament
    -0.72
    POSITIVE LOGITS
     Especially
    1.60
     ;)
    1.46
     Maybe
    1.32
     Firstly
    1.31
     ðŁĻĤ
    1.31
     :)
    1.30
     Lots
    1.30
     :-)
    1.26
     Particularly
    1.25
     Hopefully
    1.24
    Act Density 0.580%

    No Known Activations