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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    sentences that conclude or summarize thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.89
     satell
    -0.88
     volunte
    -0.88
     affili
    -0.87
     commer
    -0.82
     proport
    -0.81
     encount
    -0.79
    enture
    -0.77
     strugg
    -0.76
     stocking
    -0.74
    POSITIVE LOGITS
     "'
    1.61
     Apparently
    1.41
     "âĢ¦
    1.38
     Surely
    1.37
     Asked
    1.37
     Suddenly
    1.30
     Turns
    1.27
     "[
    1.26
     Nope
    1.25
     "
    1.24
    Act Density 0.336%

    No Known Activations