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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" and its associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     specials
    -0.17
    LS
    -0.15
    N
    -0.15
     Trom
    -0.15
     special
    -0.15
    anders
    -0.14
    iph
    -0.14
    jm
    -0.14
     Lar
    -0.14
    æº
    -0.14
    POSITIVE LOGITS
    OPSIS
    0.17
    iationException
    0.17
    azÄĥ
    0.16
    rale
    0.15
    DidChange
    0.15
    .hxx
    0.15
    essa
    0.15
    ãĥ¼ãĥł
    0.14
    #
    0.14
    pie
    0.14
    Act Density 0.038%

    No Known Activations