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

    Neuronpedia

    INDEX
    Explanations

    specific mathematical symbols and notations used in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tribute
    -0.15
    autos
    -0.15
    åħī
    -0.14
    tributes
    -0.14
    quette
    -0.14
    etting
    -0.13
    ialis
    -0.13
    vise
    -0.13
    åĬĽçļĦ
    -0.13
    plit
    -0.13
    POSITIVE LOGITS
    ova
    0.26
    ovo
    0.22
    ovy
    0.19
    ĺħ
    0.18
    izin
    0.17
    inh
    0.16
    çļĦæĥħ
    0.16
    çļĦå°ı
    0.16
    ÄįÃŃ
    0.15
    inand
    0.14
    Act Density 0.085%

    No Known Activations