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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "to" as it relates to actions or purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amina
    -0.17
    ething
    -0.16
    cribe
    -0.15
    ehler
    -0.14
    ofs
    -0.14
     amplified
    -0.14
    colo
    -0.14
    ign
    -0.14
     Holt
    -0.13
    èĶµ
    -0.13
    POSITIVE LOGITS
     ache
    0.15
     attempt
    0.15
    509
    0.15
     ensure
    0.14
     guarantee
    0.14
    an
    0.14
    334
    0.14
     обеÑģпеÑĩ
    0.14
    to
    0.14
    512
    0.14
    Act Density 0.177%

    No Known Activations