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

    Neuronpedia

    INDEX
    Explanations

    numerical values represented in dollars, pounds, or quantities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating quantities greater than a specified number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Finder
    -0.72
     derog
    -0.69
    NEY
    -0.68
     Bomber
    -0.65
    ilic
    -0.65
    ãĤ¼ãĤ¦ãĤ¹
    -0.62
     Pioneer
    -0.62
    Ô
    -0.60
    oris
    -0.60
    OSP
    -0.59
    POSITIVE LOGITS
    whelming
    0.87
    capacity
    0.80
    lyak
    0.79
    represent
    0.76
    arching
    0.71
    fif
    0.71
    iw
    0.69
    perties
    0.68
    atos
    0.67
     1500
    0.67
    Act Density 0.055%

    No Known Activations