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

    Neuronpedia

    INDEX
    Explanations

    references to academic journals or articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -1.13
     Theſe
    -1.10
     Diſ
    -1.10
     itſelf
    -1.06
     Beſ
    -1.05
     Reſ
    -1.04
     ་་
    -1.03
     raiſ
    -1.03
     Anſ
    -1.02
     Inſ
    -0.98
    POSITIVE LOGITS
     J
    3.05
    J
    2.73
     j
    2.02
    j
    1.52
    Ｊ
    1.14
    JJ
    1.07
     ج
    1.07
     Дж
    1.05
     JJ
    1.01
     K
    1.00
    Act Density 0.159%

    No Known Activations