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

    Neuronpedia

    INDEX
    Explanations

    phrases or clauses that introduce a contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Filmographie
    -0.58
     Oberlin
    -0.57
     Laine
    -0.57
     Denison
    -0.56
     perjury
    -0.54
     FontAwesome
    -0.53
     prefent
    -0.53
     CAG
    -0.52
     Valentina
    -0.52
     vermis
    -0.52
    POSITIVE LOGITS
     برانيه
    0.90
     also
    0.87
    ;">
    0.73
     مشين
    0.71
     even
    0.70
     Wicidata
    0.69
    ]:
    0.68
     snippetHide
    0.68
    таратура
    0.67
    makeConstraints
    0.66
    Act Density 0.093%

    No Known Activations