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

    Neuronpedia

    INDEX
    Explanations

    references to top-ranked lists and achievements in various categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     שוליים
    -0.97
    saraba
    -0.82
     propOrder
    -0.73
    DIPSETTING
    -0.73
     TextAppearance
    -0.73
    igshid
    -0.72
    قایناق‌لار
    -0.72
    ">//
    -0.71
    writeFieldEnd
    -0.71
    Referencie
    -0.68
    POSITIVE LOGITS
     ranking
    0.68
     Top
    0.59
     rankings
    0.58
    ランキング
    0.57
     ranked
    0.56
    Top
    0.55
    TOP
    0.54
     TOP
    0.54
     Best
    0.54
     listOf
    0.53
    Act Density 0.195%

    No Known Activations