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

    Neuronpedia

    INDEX
    Explanations

    references to different types of pasta

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phosa
    -0.59
    astify
    -0.53
    IndentedString
    -0.52
    RTEX
    -0.52
    zzleHttp
    -0.51
    pexpr
    -0.50
     queſta
    -0.49
    LookAnd
    -0.48
    inghouse
    -0.47
     dezelve
    -0.47
    POSITIVE LOGITS
     pasta
    0.71
     Pasta
    0.66
     Spaghetti
    0.65
     noodle
    0.64
    AddTagHelper
    0.63
     spaghetti
    0.63
     noodles
    0.61
    Spaghetti
    0.61
    Pasta
    0.57
     Noodles
    0.53
    Act Density 0.401%

    No Known Activations