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

    Neuronpedia

    INDEX
    Explanations

    elements related to decision-making and evaluating options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unner
    -0.17
    inand
    -0.16
    éĿĪ
    -0.15
    ayette
    -0.15
    bsolute
    -0.14
    quiv
    -0.14
    AIT
    -0.14
    åIJĪåIJĮ
    -0.14
    abit
    -0.13
     Hobby
    -0.13
    POSITIVE LOGITS
     seemed
    0.23
     except
    0.22
     until
    0.22
    ãĢĤãģĹãģĭãģĹ
    0.20
     seeming
    0.19
     Until
    0.18
     superficial
    0.18
     dut
    0.18
     Except
    0.18
     Yet
    0.18
    Act Density 0.313%

    No Known Activations