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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references to legal classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĿãģĹãģ¦
    -0.16
     chó
    -0.15
    iten
    -0.15
    ASET
    -0.14
    uco
    -0.14
    ugging
    -0.14
     possesses
    -0.13
    ackages
    -0.13
     cazzo
    -0.13
    ugg
    -0.13
    POSITIVE LOGITS
    ADER
    0.14
     Ùħرک
    0.14
    ATUS
    0.14
    pri
    0.14
     Método
    0.14
    åį
    0.14
    _beam
    0.14
    ÙĦاÙħ
    0.13
    raquo
    0.13
    esson
    0.13
    Act Density 0.004%

    No Known Activations