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

    Neuronpedia

    INDEX
    Explanations

    transitional phrases and contrasting ideas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĶ±äºİ
    -0.15
    omanip
    -0.15
    wort
    -0.14
    umhur
    -0.14
    onte
    -0.14
    inous
    -0.13
    >'.↵
    -0.13
    ÄĻż
    -0.13
    anca
    -0.13
    due
    -0.13
    POSITIVE LOGITS
     few
    0.28
     taken
    0.25
     maybe
    0.23
     what
    0.21
     beneath
    0.21
     credit
    0.20
     context
    0.20
     perhaps
    0.20
     such
    0.20
    few
    0.20
    Act Density 0.276%

    No Known Activations