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

    Neuronpedia

    INDEX
    Explanations

    phrases related to media coverage and public perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    廳
    -0.14
    à¹ĥà¸Ī
    -0.13
    orton
    -0.13
    ffa
    -0.13
    uce
    -0.13
    orney
    -0.13
    Rejected
    -0.13
     ëĦĺ
    -0.13
    lsi
    -0.13
    aat
    -0.13
    POSITIVE LOGITS
     media
    0.85
    media
    0.71
     Media
    0.67
     press
    0.65
    åªĴä½ĵ
    0.64
    Media
    0.63
    -media
    0.63
     MEDIA
    0.60
    .media
    0.52
    _media
    0.52
    Act Density 0.345%

    No Known Activations