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

    Neuronpedia

    INDEX
    Explanations

    terms associated with reckless or foolish behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enos
    -0.16
     ÙģÙĪ
    -0.15
    ampo
    -0.14
    _CIPHER
    -0.14
    uxe
    -0.14
    507
    -0.14
    UsageId
    -0.14
    .PLL
    -0.14
    .dw
    -0.14
     mdi
    -0.14
    POSITIVE LOGITS
    iker
    0.15
    162
    0.15
    163
    0.15
    /fast
    0.15
    simp
    0.15
    nes
    0.15
    acher
    0.14
    emes
    0.14
     care
    0.14
    andro
    0.14
    Act Density 0.007%

    No Known Activations