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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gpt-3.5-turbo

    mathematical functions and their parameters in a statistical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bourg
    -0.86
    ilage
    -0.77
     Lauder
    -0.76
    nesota
    -0.70
    ãĥīãĥ©
    -0.68
    bro
    -0.67
     manag
    -0.67
    iewicz
    -0.66
    ufact
    -0.66
    hower
    -0.65
    POSITIVE LOGITS
    Ï
    1.58
    α
    1.55
    Î
    1.51
    ο
    1.51
    ι
    1.50
    á½
    1.43
    ε
    1.39
    ÏĦ
    1.36
    λ
    1.34
    Ïģ
    1.33
    Act Density 0.022%

    No Known Activations