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

    Neuronpedia

    INDEX
    Explanations

    discussions around the media's treatment of controversial subjects, particularly regarding societal perceptions and biases

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.83
     Theſe
    -0.81
    RectangleBorder
    -0.79
    StoryboardSegue
    -0.76
     Beſ
    -0.75
     Référence
    -0.74
    AddTagHelper
    -0.72
     ſte
    -0.70
     vixion
    -0.69
     Superhosts
    -0.69
    POSITIVE LOGITS
    afficheront
    0.42
     siglos
    0.41
    ugc
    0.40
    万美元
    0.40
     cientos
    0.39
     nasel
    0.39
     được
    0.39
     vele
    0.38
     cumplido
    0.38
    devServer
    0.37
    Act Density 0.146%

    No Known Activations