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

    Neuronpedia

    INDEX
    Explanations

    references to categories of identity and societal classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    httphttps
    -0.50
    体は
    -0.47
    Geplaatst
    -0.44
     Tatsache
    -0.42
     Aussicht
    -0.41
    rungsseite
    -0.40
     ujedno
    -0.40
     Fähigkeit
    -0.38
     Anhänger
    -0.38
    heça
    -0.38
    POSITIVE LOGITS
    ”,
    0.59
    principalTable
    0.56
    AISSEE
    0.55
     OMITBAD
    0.55
    ”.
    0.52
    .”
    0.51
    “,
    0.50
    ’,
    0.50
     getById
    0.49
    ”!
    0.49
    Act Density 1.469%

    No Known Activations