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

    Neuronpedia

    INDEX
    Explanations

    references to duality and mutual relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quier
    -0.18
     all
    -0.17
    ight
    -0.15
    ima
    -0.15
    iras
    -0.15
    ocate
    -0.15
    onte
    -0.15
     alone
    -0.15
     maybe
    -0.14
    nbr
    -0.14
    POSITIVE LOGITS
     Kurum
    0.17
    bserv
    0.16
     birden
    0.16
    LLLL
    0.15
    pron
    0.14
     equally
    0.14
    ignet
    0.14
    847
    0.14
    ABCDEFGHIJKLMNOP
    0.14
    illery
    0.14
    Act Density 0.190%

    No Known Activations