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

    Neuronpedia

    INDEX
    Explanations

    various forms of punctuation and numerical representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TimeZone
    -0.16
    ापन
    -0.14
    çĶŁçļĦ
    -0.14
     fault
    -0.14
    ixa
    -0.13
     Couple
    -0.13
     bevor
    -0.13
    .LoadScene
    -0.13
     whe
    -0.13
    eryl
    -0.13
    POSITIVE LOGITS
    rlen
    0.16
     Flynn
    0.15
     Mach
    0.14
    лÑıÑħ
    0.14
    UILD
    0.14
    okud
    0.14
    Introduced
    0.14
     mach
    0.14
    roperties
    0.13
     radius
    0.13
    Act Density 0.136%

    No Known Activations