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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of news sources

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "The" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CVE
    -0.83
     sidel
    -0.68
     colle
    -0.64
     inval
    -0.63
     behold
    -0.63
     deduct
    -0.62
     rein
    -0.62
     beware
    -0.60
    _.
    -0.60
     unsurprisingly
    -0.58
    POSITIVE LOGITS
     Chronicle
    1.00
     Associated
    0.99
     Courier
    0.96
    aron
    0.91
     Huffington
    0.90
     Washington
    0.86
     Vaugh
    0.85
     Desert
    0.85
     Herald
    0.85
     Register
    0.84
    Act Density 0.040%

    No Known Activations