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

    Neuronpedia

    INDEX
    Explanations

    phrases related to artificial intelligence and its implications in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.57
    enderror
    -0.55
     kasarigan
    -0.51
    EndContext
    -0.49
    AccessorTable
    -0.49
     PeEnEo
    -0.45
     defaultstate
    -0.45
    GEBURTSDATUM
    -0.45
    saraba
    -0.44
    الإنجليزية
    -0.42
    POSITIVE LOGITS
    Patch
    0.39
     Mulher
    0.39
    felizmente
    0.38
     merely
    0.38
    rivit
    0.38
     marginal
    0.38
     glorified
    0.37
    Platz
    0.37
    PATCH
    0.37
    zension
    0.36
    Act Density 0.697%

    No Known Activations