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

    Neuronpedia

    INDEX
    Explanations

    phrases related to current events and news headlines

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¨ãĥ«
    -0.79
    Ö¼
    -0.76
    vised
    -0.76
    enz
    -0.72
    ibe
    -0.71
    iffe
    -0.71
    FW
    -0.71
    aria
    -0.70
    oya
    -0.69
    ãĥ¼ãĤ¯
    -0.69
    POSITIVE LOGITS
     pundits
    0.91
     rumors
    0.88
     tensions
    0.85
     commentators
    0.81
     speculation
    0.78
     legions
    0.77
     rumours
    0.77
     policymakers
    0.76
     lawmakers
    0.75
     photographers
    0.75
    Act Density 0.246%

    No Known Activations