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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "to" followed by actions or goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Shir
    -0.81
    ois
    -0.76
     Taro
    -0.71
     Baird
    -0.70
    addObject
    -0.70
    卉
    -0.64
     Siro
    -0.64
    Cloth
    -0.63
    THO
    -0.63
    jstor
    -0.62
    POSITIVE LOGITS
     BorderRadius
    0.76
     Helle
    0.71
    Gets
    0.70
    AsUp
    0.69
    Доставка
    0.69
     rid
    0.69
    omitempty
    0.68
    Gotta
    0.68
     setOpen
    0.67
    Kap
    0.66
    Act Density 0.044%

    No Known Activations