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

    Neuronpedia

    INDEX
    Explanations

    references to lists or rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ila
    -0.16
     clip
    -0.16
    212
    -0.15
     Clip
    -0.15
     Raq
    -0.15
     jack
    -0.14
     hind
    -0.14
    客
    -0.14
    263
    -0.14
     Americans
    -0.13
    POSITIVE LOGITS
    uron
    0.16
    uffman
    0.15
    xit
    0.15
    ãģĹãĤĩ
    0.14
    Ñģли
    0.14
    reuse
    0.14
    _magic
    0.14
    omid
    0.14
     ÑĢайонÑĥ
    0.14
    áng
    0.14
    Act Density 0.110%

    No Known Activations