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

    Neuronpedia

    INDEX
    Explanations

    numerical values and symbols commonly found in data sets and programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    91
    -0.20
    94
    -0.20
    92
    -0.19
    921
    -0.19
    93
    -0.17
     Foley
    -0.16
    187
    -0.16
    elder
    -0.15
    Âĭ
    -0.15
     <!--[
    -0.15
    POSITIVE LOGITS
     Greg
    0.48
    Greg
    0.42
     Gregory
    0.38
     Craig
    0.34
    greg
    0.33
     Gregg
    0.31
    Craig
    0.29
    597
    0.29
     cfg
    0.25
     Roger
    0.25
    Act Density 0.034%

    No Known Activations