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

    Neuronpedia

    INDEX
    Explanations

    numbers that indicate a position or quantity

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "one of" followed by a numeric value or a group reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    culosis
    -0.76
     lapt
    -0.67
     onwards
    -0.64
    iture
    -0.63
    anse
    -0.63
     IPM
    -0.62
     satell
    -0.61
    gee
    -0.60
    enery
    -0.60
    ikarp
    -0.60
    POSITIVE LOGITS
    icial
    0.79
    arching
    0.74
    ounding
    0.67
     sorts
    0.64
    hedral
    0.64
    apest
    0.64
    ãĤ¨
    0.63
    kefeller
    0.63
     richest
    0.62
    icer
    0.62
    Act Density 0.058%

    No Known Activations