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

    Neuronpedia

    INDEX
    Explanations

    negative statements or phrases indicating refusal or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    íĦ
    -0.16
    .scalablytyped
    -0.15
     asset
    -0.15
    丸
    -0.15
    MD
    -0.14
    FD
    -0.14
     Norris
    -0.13
    hiba
    -0.13
    aklı
    -0.13
    lds
    -0.13
    POSITIVE LOGITS
    elts
    0.19
    ï¿
    0.15
    andro
    0.15
     Herrera
    0.15
     Trit
    0.14
    OPY
    0.14
     Lar
    0.14
     Integrity
    0.14
    oka
    0.13
    edList
    0.13
    Act Density 0.001%

    No Known Activations