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

    Neuronpedia

    INDEX
    Explanations

    mentions of reading and blog posts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     nawr
    -0.61
    Abit
    -0.55
    DeleteBehavior
    -0.51
    ⇨
    -0.51
    UIFont
    -0.51
    Charsets
    -0.51
    RTGC
    -0.51
     Paglinawan
    -0.50
    AfterEach
    -0.50
    Koordin
    -0.50
    POSITIVE LOGITS
     disagre
    1.35
     intersper
    1.33
     apprehen
    1.19
     pamph
    1.13
     unspeak
    1.12
     unwarran
    1.11
     maneu
    1.07
     gaily
    1.06
     uninten
    1.06
     ftre
    1.05
    Act Density 0.567%

    No Known Activations