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

    Neuronpedia

    INDEX
    Explanations

    phrases related to justification and reasoning in a context of social issues and race

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     []:
    -0.57
     visst
    -0.54
    IonicModule
    -0.50
    왔
    -0.48
    JNIEnv
    -0.48
    Work
    -0.47
    mailto
    -0.45
     aras
    -0.45
     Souver
    -0.45
     yhte
    -0.44
    POSITIVE LOGITS
    HasForeignKey
    0.78
     незавершена
    0.73
    Vidite
    0.71
     Catawiki
    0.69
     שוליים
    0.59
     widows
    0.59
    anasia
    0.59
    ★☆
    0.58
    ++
    0.58
     DIB
    0.58
    Act Density 0.041%

    No Known Activations