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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is demanding something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "that"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¨ãĥ«
    -0.69
    ãĥ¬
    -0.66
     Hop
    -0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
    Ö
    -0.65
     Ups
    -0.61
    ãĤ§
    -0.60
    ãĥ¡
    -0.60
    cience
    -0.59
     sidx
    -0.59
    POSITIVE LOGITS
    soever
    0.74
     electors
    0.72
     nomine
    0.72
     recipients
    0.69
     clinicians
    0.68
    chers
    0.67
    cher
    0.64
     users
    0.64
    lav
    0.64
    amera
    0.64
    Act Density 0.179%

    No Known Activations