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

    Neuronpedia

    INDEX
    Explanations

    collaborative or cooperative relationships and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allon
    -0.16
    ensa
    -0.15
    OND
    -0.15
    Ĥ¹
    -0.15
    ãĥ¼ãĥ«
    -0.15
    ungs
    -0.15
    ayet
    -0.14
    alborg
    -0.14
    idel
    -0.14
    perial
    -0.14
    POSITIVE LOGITS
     co
    0.40
    equal
    0.23
    ales
    0.23
    arser
    0.19
     Co
    0.19
    hes
    0.18
    hab
    0.17
     equal
    0.17
    /co
    0.17
    equals
    0.17
    Act Density 0.017%

    No Known Activations