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

    Neuronpedia

    INDEX
    Explanations

    numeric values represented as currency

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hollow
    -0.72
     Triangle
    -0.67
     Sapphire
    -0.67
     17
    -0.63
     26
    -0.63
     Ichigo
    -0.63
     Inher
    -0.63
     27
    -0.62
     22
    -0.61
     Roh
    -0.61
    POSITIVE LOGITS
    98
    1.22
    96
    1.17
    86
    1.15
    89
    1.12
    93
    1.12
    95
    1.11
    97
    1.11
    87
    1.10
    99
    1.09
    92
    1.08
    Act Density 0.184%

    No Known Activations