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

    Neuronpedia

    INDEX
    Explanations

    phrases that express goals and efforts towards achieving objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ises
    -0.18
    oran
    -0.16
     narrator
    -0.14
    ÑĢоÑİ
    -0.14
    oid
    -0.14
    alon
    -0.14
     Ballet
    -0.14
    imes
    -0.13
    ISE
    -0.13
    irt
    -0.13
    POSITIVE LOGITS
    -scalable
    0.15
    iang
    0.15
    getti
    0.15
    ácil
    0.14
    ãĥªãĥ¼
    0.14
    803
    0.14
    aq
    0.14
    ¨
    0.14
    501
    0.14
     Mattis
    0.14
    Act Density 0.014%

    No Known Activations