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

    Neuronpedia

    INDEX
    Explanations

    dollar amounts mentioned in financial contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to monetary amounts and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amac
    -0.60
     âĵĺ
    -0.58
    :(
    -0.55
     ACTIONS
    -0.54
    Engineers
    -0.54
     citiz
    -0.53
    NetMessage
    -0.53
    grounds
    -0.52
     Ashes
    -0.51
    Mania
    -0.51
    POSITIVE LOGITS
    000
    1.36
    00
    1.05
    500
    0.96
    800
    0.89
    075
    0.88
    600
    0.85
    995
    0.85
    200
    0.81
    700
    0.81
    040
    0.80
    Act Density 0.071%

    No Known Activations