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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "are" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \grid
    -0.16
    illa
    -0.14
    nat
    -0.13
    spe
    -0.13
     ÑĤÑĢÑĥда
    -0.13
     spokeswoman
    -0.13
    igin
    -0.13
    acha
    -0.13
    ẩn
    -0.13
    scope
    -0.13
    POSITIVE LOGITS
    vd
    0.15
    ìĽħ
    0.15
    ulle
    0.15
    ugas
    0.14
    /is
    0.14
    ullo
    0.14
    ames
    0.13
    ITCH
    0.13
     Rubin
    0.13
    ´Ŀ
    0.13
    Act Density 0.033%

    No Known Activations