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

    Neuronpedia

    INDEX
    Explanations

    years mentioned in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ree
    -0.18
    170
    -0.16
    700
    -0.15
    684
    -0.15
    lene
    -0.14
     Å
    -0.14
     grunt
    -0.14
    609
    -0.14
     Seah
    -0.14
     slog
    -0.14
    POSITIVE LOGITS
    9
    0.21
    ९
    0.20
     Nin
    0.19
     fri
    0.18
    19
    0.18
     ninete
    0.18
    Û¹
    0.18
    Ù©
    0.17
    962
    0.17
    905
    0.17
    Act Density 0.030%

    No Known Activations