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

    Neuronpedia

    INDEX
    Explanations

    specific references to authors or contributors in academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑıÑģ
    -0.16
    ectors
    -0.15
    onto
    -0.14
    ezi
    -0.14
    ration
    -0.14
    и
    -0.14
    AJ
    -0.14
    ại
    -0.14
    went
    -0.14
    ιά
    -0.14
    POSITIVE LOGITS
    alars
    0.16
    ænd
    0.15
    hammer
    0.15
    ány
    0.15
     خاÙħ
    0.15
    à¤Ńà¤Ĺ
    0.15
    ÄįÃŃ
    0.15
     Hammer
    0.14
     Coff
    0.14
    GF
    0.14
    Act Density 0.004%

    No Known Activations