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

    Neuronpedia

    INDEX
    Explanations

    dates or years

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their significance in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     facult
    -0.82
     finalized
    -0.75
     formally
    -0.74
     advantageous
    -0.73
     cod
    -0.71
    ©¶æ
    -0.70
     conserv
    -0.69
     administr
    -0.69
     agreed
    -0.67
     footing
    -0.67
    POSITIVE LOGITS
     Especially
    1.07
     Everywhere
    1.04
     Thousands
    1.04
     Watching
    1.03
     Surely
    1.02
     Places
    0.93
     Millions
    0.92
     Suddenly
    0.91
     Particularly
    0.89
     Wouldn
    0.89
    Act Density 0.780%

    No Known Activations