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

    Neuronpedia

    INDEX
    Explanations

    statements regarding reasons or justifications for decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Woj
    -0.18
    OfClass
    -0.15
    iest
    -0.14
    assen
    -0.14
    ennent
    -0.14
    æľĢçµĤ
    -0.14
    iban
    -0.14
     Halk
    -0.14
    éĻħ
    -0.14
    eree
    -0.14
    POSITIVE LOGITS
    letic
    0.18
    egen
    0.15
     gated
    0.15
    ritel
    0.15
     GIF
    0.15
    eczy
    0.15
    _pv
    0.15
    зÑĥ
    0.14
     teg
    0.14
    äº
    0.14
    Act Density 0.028%

    No Known Activations