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

    Neuronpedia

    INDEX
    Explanations

    phrases that express irony or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ographics
    -0.16
    adolu
    -0.15
    amas
    -0.15
    .SC
    -0.15
    inz
    -0.15
     Bones
    -0.14
    yw
    -0.14
    herits
    -0.14
    aley
    -0.14
     åģ
    -0.14
    POSITIVE LOGITS
    665
    0.16
    عاÙĨ
    0.16
    ãģ£ãģ±
    0.15
     PRI
    0.15
     Mons
    0.15
    stile
    0.15
    /pi
    0.14
    PRI
    0.14
    shima
    0.14
     Nun
    0.14
    Act Density 0.192%

    No Known Activations