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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that end with a full stop

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express strong assertions or definitive statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favorably
    -1.05
     favorable
    -1.00
     unfavorable
    -0.97
     honored
    -0.97
     favoring
    -0.96
     center
    -0.96
     favor
    -0.96
     leveled
    -0.96
     honoring
    -0.95
     paycheck
    -0.94
    POSITIVE LOGITS
     Whilst
    2.03
     £
    1.52
     Ukip
    1.50
     Firstly
    1.49
    £
    1.44
    Labour
    1.40
     UKIP
    1.38
     Labour
    1.38
     Britons
    1.36
     ITV
    1.35
    Act Density 0.591%

    No Known Activations