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

    Neuronpedia

    INDEX
    Explanations

    occurrences of conjunctions and prepositions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çŁ
    -0.15
    edian
    -0.15
    iche
    -0.14
    izard
    -0.14
    entin
    -0.13
     ration
    -0.13
    adden
    -0.13
    bt
    -0.13
    ayo
    -0.13
    ostel
    -0.13
    POSITIVE LOGITS
    oler
    0.16
    itori
    0.15
    .vn
    0.15
    åĥ
    0.15
    uno
    0.14
    aid
    0.14
    066
    0.14
     mere
    0.14
     Century
    0.14
    hma
    0.13
    Act Density 0.062%

    No Known Activations