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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coop
    -0.14
    ầm
    -0.14
    olver
    -0.14
    metro
    -0.14
    "label
    -0.14
    ойно
    -0.13
    wap
    -0.13
    orama
    -0.13
     Sm
    -0.13
    RAY
    -0.13
    POSITIVE LOGITS
    eza
    0.19
    442
    0.18
    anner
    0.15
    teri
    0.15
    htub
    0.15
    fst
    0.15
    lesen
    0.14
    406
    0.14
    leaf
    0.14
    /th
    0.14
    Act Density 0.056%

    No Known Activations