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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions and processes in technical or instructional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eton
    -0.16
    afone
    -0.16
     Cần
    -0.14
    allis
    -0.14
    foon
    -0.13
    zn
    -0.13
    ļĮ
    -0.13
    ActionCreators
    -0.13
    abei
    -0.13
    assen
    -0.13
    POSITIVE LOGITS
     only
    0.27
     rather
    0.27
     instead
    0.23
     neither
    0.22
    çļĦæĺ¯
    0.22
    rather
    0.21
    ãģ§ãģ¯ãģªãģı
    0.21
     именно
    0.21
     either
    0.20
     something
    0.19
    Act Density 0.392%

    No Known Activations