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

    Neuronpedia

    INDEX
    Explanations

    references to meteoric rises or exponential growth

    oai_token-act-pair · gpt-3.5-turbo

    terms related to successful or prominent achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Luxem
    -0.74
    xon
    -0.66
    cross
    -0.64
    oldown
    -0.63
    phal
    -0.62
    okia
    -0.62
    SG
    -0.60
     Hog
    -0.60
     nowhere
    -0.60
     Punch
    -0.60
    POSITIVE LOGITS
     mete
    1.04
     fract
    1.02
    ors
    0.91
    ures
    0.86
    è¦ļéĨĴ
    0.86
     pestic
    0.84
    ered
    0.83
    urable
    0.82
    itures
    0.82
    ets
    0.81
    Act Density 0.020%

    No Known Activations