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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "close."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osate
    -0.17
    IFIC
    -0.17
    anine
    -0.16
    anse
    -0.14
    lore
    -0.14
    atis
    -0.14
    ickle
    -0.14
    èµ·ãģĵ
    -0.14
    rock
    -0.14
    lic
    -0.14
    POSITIVE LOGITS
     proximity
    0.26
     knit
    0.22
    -caption
    0.22
     enough
    0.21
     Enough
    0.19
    ximity
    0.19
    -quarters
    0.18
    -packed
    0.18
    erto
    0.18
    /close
    0.18
    Act Density 0.016%

    No Known Activations