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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "added."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iao
    -0.16
    illion
    -0.15
    SharedPtr
    -0.15
    à¹Īà¸ĩà¸Ĥ
    -0.14
    éı
    -0.14
     Strom
    -0.14
    енко
    -0.13
    inh
    -0.13
    aster
    -0.13
    [image
    -0.13
    POSITIVE LOGITS
    endum
    0.23
    forman
    0.17
    uce
    0.16
    thur
    0.16
    gend
    0.16
    æķħ
    0.16
    zers
    0.15
    gressor
    0.15
    _HERSHEY
    0.15
    ĥ½
    0.15
    Act Density 0.015%

    No Known Activations