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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aya
    -0.19
    apesh
    -0.16
    ä½ľ
    -0.14
    acht
    -0.14
    pal
    -0.14
    afil
    -0.14
    ka
    -0.14
    &e
    -0.14
    ControlEvents
    -0.14
    erte
    -0.13
    POSITIVE LOGITS
    ying
    0.20
    okit
    0.19
    ether
    0.18
    gether
    0.16
    ÙĪرات
    0.16
    sko
    0.16
    ogle
    0.16
    hung
    0.15
    oting
    0.15
    asting
    0.15
    Act Density 0.394%

    No Known Activations