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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" in various grammatical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preposition "to" followed by word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desmotivaciones
    -0.53
     íntimo
    -0.49
     kasarigan
    -0.48
     bolig
    -0.48
     pihaknya
    -0.48
     Sebab
    -0.48
     pretože
    -0.47
     ponieważ
    -0.46
     psicológico
    -0.46
     forskellige
    -0.46
    POSITIVE LOGITS
     my
    0.59
     yummy
    0.57
     your
    0.55
     you
    0.53
     lazy
    0.52
    !
    0.50
     awesome
    0.50
     pesky
    0.49
    !).
    0.49
    󠁮
    0.48
    Act Density 0.037%

    No Known Activations