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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ota
    -0.17
    anth
    -0.16
     propos
    -0.15
    ÃŃm
    -0.14
     worker
    -0.14
    oga
    -0.14
     Ùħست
    -0.14
    íļį
    -0.13
     Ches
    -0.13
    510
    -0.13
    POSITIVE LOGITS
     Cake
    0.44
    Cake
    0.42
     cake
    0.40
    cake
    0.37
     cakes
    0.33
     bake
    0.28
     Bake
    0.27
    cakes
    0.25
    .ct
    0.24
    ecake
    0.23
    Act Density 0.002%

    No Known Activations