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

    Neuronpedia

    INDEX
    Explanations

    years mentioned in sentences

    oai_token-act-pair · gpt-3.5-turbo

    significant years related to historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Dialogue
    -0.70
    morrow
    -0.66
    olar
    -0.65
    Edge
    -0.62
     hereby
    -0.62
    cko
    -0.61
    BOOK
    -0.61
     snipp
    -0.59
     unres
    -0.59
     lawy
    -0.59
    POSITIVE LOGITS
    ãĥĥãĥī
    0.86
    -'
    0.86
    ãĥŁ
    0.75
    abi
    0.74
    ãĥ¼ãĥĨãĤ£
    0.71
    chev
    0.69
     Coliseum
    0.69
    é¾įå¥ij士
    0.69
     Sears
    0.68
     Takeru
    0.67
    Act Density 0.159%

    No Known Activations