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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating advantages or disadvantages

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.77
    yntaxException
    -0.72
    (!__
    -0.68
    ikbaar
    -0.68
     مشين
    -0.60
    Fordítás
    -0.59
     Chwiliwch
    -0.59
    adple
    -0.58
    มาณ
    -0.57
    Tentang
    -0.57
    POSITIVE LOGITS
    ly
    1.16
    fully
    0.96
    mente
    0.85
    ably
    0.72
    LY
    0.72
    ally
    0.71
    ately
    0.70
    ically
    0.70
    tly
    0.70
    tably
    0.69
    Act Density 0.081%

    No Known Activations