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

    Neuronpedia

    INDEX
    Explanations

    dollar amounts and financial information

    oai_token-act-pair · gpt-3.5-turbo

    currency amounts and prices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nare
    -0.83
     Gors
    -0.78
     pron
    -0.70
     Tall
    -0.67
     Samar
    -0.66
     demol
    -0.66
     Dare
    -0.64
     Favor
    -0.64
     Bene
    -0.64
     Amer
    -0.63
    POSITIVE LOGITS
    ©¶æ¥µ
    0.92
    false
    0.92
    $$
    0.91
    False
    0.90
    iris
    0.86
    HOME
    0.85
    remote
    0.85
    true
    0.84
    400
    0.82
    self
    0.81
    Act Density 0.064%

    No Known Activations