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

    Neuronpedia

    INDEX
    Explanations

    numerals with punctuation

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings, particularly those involving periods, indicating the conclusion of thoughts or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anooga
    -0.71
     swoop
    -0.70
     volunte
    -0.70
     intensive
    -0.69
     intellig
    -0.67
     scrim
    -0.66
     dere
    -0.66
     leasing
    -0.64
     interf
    -0.64
     manufacturing
    -0.64
    POSITIVE LOGITS
    Pg
    1.61
    ...]
    1.33
    âĢ¦]
    1.24
    emphasis
    1.20
    src
    1.20
    note
    1.17
    131
    1.15
    xxx
    1.13
    141
    1.11
    124
    1.10
    Act Density 0.033%

    No Known Activations