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

    Neuronpedia

    INDEX
    Explanations

    references to specific programming classes or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    govor
    -0.53
     sledo
    -0.53
    ربعة
    -0.47
     pomo
    -0.47
    inā
    -0.47
    ėl
    -0.46
     keres
    -0.46
    ņa
    -0.45
    Thanx
    -0.43
    bný
    -0.43
    POSITIVE LOGITS
     Jop
    1.38
     JJ
    1.37
     jc
    1.35
     J
    1.34
     JE
    1.34
     Ja
    1.31
     JP
    1.30
     Jays
    1.29
     JAS
    1.29
     JC
    1.29
    Act Density 2.698%

    No Known Activations