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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "on" and related phrases indicating continuation or reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hint
    -0.14
    ãĥĵãĥ¼
    -0.14
    SizePolicy
    -0.14
    ying
    -0.13
    ï¼ł
    -0.13
     Hük
    -0.13
    _Normal
    -0.13
    Wiki
    -0.12
    ourney
    -0.12
    жив
    -0.12
    POSITIVE LOGITS
    º
    0.16
    eneg
    0.16
     [
    0.15
    oftware
    0.15
    isci
    0.14
    rades
    0.14
    ÑĮÑİ
    0.14
    uri
    0.14
     ãĢIJ
    0.14
    ugi
    0.13
    Act Density 0.049%

    No Known Activations