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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.62
    WORTH
    -0.62
    INTO
    -0.62
    -0.60
     ['$
    -0.59
    fible
    -0.58
     ddelweddau
    -0.57
    polation
    -0.57
     WORTH
    -0.56
    KELEY
    -0.56
    POSITIVE LOGITS
     Allí
    0.51
    Geographie
    0.47
    이의
    0.44
     Tapa
    0.44
    Calls
    0.43
     dort
    0.43
    ฤษ
    0.43
    AndEndTag
    0.43
    ViewGroup
    0.43
    ாய்
    0.42
    Act Density 0.131%

    No Known Activations