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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "to" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arrive
    -0.18
    entai
    -0.17
     arrives
    -0.17
    .selenium
    -0.15
    agina
    -0.14
    adir
    -0.14
     refrain
    -0.14
    rane
    -0.14
     Replies
    -0.14
    feit
    -0.14
    POSITIVE LOGITS
     see
    0.18
     deliver
    0.16
     tended
    0.16
    ting
    0.16
    ypy
    0.16
     tend
    0.16
     check
    0.15
     survey
    0.15
     collect
    0.15
    -facing
    0.15
    Act Density 0.220%

    No Known Activations