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

    Neuronpedia

    INDEX
    Explanations

    negative phrases and assertions about capabilities or possibilities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ClientSize
    -0.66
    AndEndTag
    -0.64
    },[])
    -0.58
    XmlAccessType
    -0.56
     Fruit
    -0.55
     fruit
    -0.54
    Fruit
    -0.54
    })$}
    -0.53
    webElementXpaths
    -0.52
     Flagstaff
    -0.52
    POSITIVE LOGITS
     absolue
    0.52
    Collegamenti
    0.49
    بيت
    0.48
     revanche
    0.47
    publicain
    0.47
    GUILayout
    0.47
    oherty
    0.46
    atguigu
    0.46
    ⋙
    0.46
    참고
    0.45
    Act Density 0.185%

    No Known Activations