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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "to" followed by various action or decision-related words and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ฤ
    -0.18
    ufe
    -0.16
    ouz
    -0.15
    spender
    -0.15
    ãĥ¥ãĥ¼
    -0.14
    stå
    -0.14
    setProperty
    -0.14
    vrier
    -0.14
    isplay
    -0.14
     regards
    -0.14
    POSITIVE LOGITS
     extremes
    0.17
     sleep
    0.16
     movies
    0.16
    ocket
    0.16
     Fritz
    0.15
     lengths
    0.15
     jelly
    0.15
     Howell
    0.15
     sea
    0.15
     heavens
    0.14
    Act Density 0.126%

    No Known Activations