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
     assistir
    -0.15
    anager
    -0.15
    APT
    -0.14
    assi
    -0.14
    erap
    -0.14
    AREST
    -0.14
    yi
    -0.14
    zman
    -0.14
     Lear
    -0.13
     (*)(
    -0.13
    POSITIVE LOGITS
    atak
    0.15
    pte
    0.14
     tongue
    0.14
     temporarily
    0.14
     Routes
    0.14
    588
    0.14
     nap
    0.14
    rium
    0.14
    Ton
    0.13
     ton
    0.13
    Act Density 0.015%

    No Known Activations