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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "closely" and related variations indicating proximity or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opause
    -0.18
     completeness
    -0.15
    zn
    -0.15
    efe
    -0.15
    YNC
    -0.15
    atee
    -0.14
    czy
    -0.14
    ello
    -0.14
     complete
    -0.14
    /cms
    -0.14
    POSITIVE LOGITS
     knit
    0.27
     proximity
    0.24
    -packed
    0.23
    -quarters
    0.21
    -k
    0.20
    ä¼¼
    0.19
    packed
    0.19
    -caption
    0.18
     inspection
    0.18
    -held
    0.18
    Act Density 0.021%

    No Known Activations