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

    Neuronpedia

    INDEX
    Explanations

    large numbers mentioned in the context of money or quantities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include high numerical values or financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :(
    -0.61
    rival
    -0.58
     Became
    -0.57
     DX
    -0.56
     Parables
    -0.56
     content
    -0.55
     Toast
    -0.55
     FTA
    -0.53
     ado
    -0.53
    worldly
    -0.53
    POSITIVE LOGITS
    000
    1.63
    600
    1.06
    700
    1.03
    00
    1.00
    400
    0.99
    500
    0.98
    800
    0.96
    900
    0.92
    300
    0.90
    750
    0.88
    Act Density 0.153%

    No Known Activations