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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    íĻĶ를
    -0.16
    ait
    -0.16
    gate
    -0.16
    crap
    -0.15
    ari
    -0.14
    entral
    -0.14
    ohon
    -0.14
    हन
    -0.14
    oon
    -0.14
    iser
    -0.14
    POSITIVE LOGITS
    leton
    0.15
    ibel
    0.15
    422
    0.15
    ä¸Ī
    0.15
    ellen
    0.14
    hausen
    0.14
    erview
    0.14
     ob
    0.13
    024
    0.13
    roup
    0.13
    Act Density 0.087%

    No Known Activations