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

    Neuronpedia

    INDEX
    Explanations

    integral and expectation notation in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PasswordEncoder
    -0.58
    CardContent
    -0.51
    HasBeenSet
    -0.49
    PostExecute
    -0.48
    interopRequire
    -0.48
    英
    -0.44
     Z
    -0.44
    ご
    -0.43
    apimachinery
    -0.43
     O
    -0.43
    POSITIVE LOGITS
     lenker
    0.78
     ―――――
    0.73
     auffi
    0.68
     насељу
    0.68
    最快更新
    0.67
    ſelf
    0.66
     AssemblyVersion
    0.66
     ainfi
    0.65
     abstrait
    0.63
     universale
    0.63
    Act Density 0.447%

    No Known Activations