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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "close" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anine
    -0.17
    IFIC
    -0.16
    ickle
    -0.15
    Äħż
    -0.15
    osate
    -0.15
    èµ·ãģĵ
    -0.15
    dan
    -0.15
    te
    -0.14
    rette
    -0.14
    926
    -0.14
    POSITIVE LOGITS
     proximity
    0.30
    -caption
    0.23
     knit
    0.23
    by
    0.21
    ximity
    0.21
     vicinity
    0.21
     enough
    0.21
     quarters
    0.20
    prox
    0.20
    -by
    0.20
    Act Density 0.016%

    No Known Activations