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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reporting and covering news and events

    oai_token-act-pair · gpt-3.5-turbo

    references to journalism and media coverage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.80
    terness
    -0.79
    appointed
    -0.70
    ĸļ
    -0.69
     counselors
    -0.69
    aldo
    -0.69
    borgh
    -0.66
    nery
    -0.66
     teasp
    -0.65
     tasted
    -0.64
    POSITIVE LOGITS
     developments
    0.99
     events
    0.93
    events
    0.83
     topics
    0.83
     news
    0.81
    ROR
    0.81
     scandals
    0.76
    aturday
    0.76
     Stories
    0.74
     matters
    0.72
    Act Density 0.271%

    No Known Activations