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

    Neuronpedia

    INDEX
    Explanations

    direct requests or demands in sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "that" in a context of requests or demands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ§
    -0.74
    ãĤ¨ãĥ«
    -0.71
    ands
    -0.68
    ãĥ¬
    -0.67
    pring
    -0.67
    STAR
    -0.67
    onder
    -0.66
    Soul
    -0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
    ocaust
    -0.64
    POSITIVE LOGITS
     users
    0.81
    soever
    0.80
     programmers
    0.79
     visitors
    0.77
     motorists
    0.76
     accompany
    0.76
    chers
    0.75
     borrowers
    0.75
     recipients
    0.74
     electors
    0.74
    Act Density 0.102%

    No Known Activations