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

    Neuronpedia

    INDEX
    Explanations

    numerical values preceded by a currency symbol

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blaz
    -0.65
     literature
    -0.63
    ellar
    -0.63
    illance
    -0.62
     Lilly
    -0.61
    rog
    -0.61
     Doodle
    -0.60
    birds
    -0.59
     flap
    -0.59
    ighting
    -0.57
    POSITIVE LOGITS
     approx
    1.05
     960
    0.94
     750
    0.87
     660
    0.86
     whopping
    0.86
     EUR
    0.86
     120
    0.86
     1280
    0.85
     roughly
    0.85
     ¥
    0.84
    Act Density 0.426%

    No Known Activations