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

    Neuronpedia

    INDEX
    Explanations

    instances of contrasting conjunctions that signal a change in the narrative or argument

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ombat
    -0.17
    oulder
    -0.17
    ullan
    -0.17
    ndon
    -0.15
     âĸĪ
    -0.15
    ught
    -0.14
    ariat
    -0.14
    éļİ
    -0.14
    é»
    -0.14
    reso
    -0.14
    POSITIVE LOGITS
    ha
    0.14
     groin
    0.14
    æ¼
    0.14
    uan
    0.14
    hammer
    0.14
    ibs
    0.14
     DataColumn
    0.14
    rod
    0.14
    dbl
    0.13
    ģ
    0.13
    Act Density 0.083%

    No Known Activations