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

    Neuronpedia

    INDEX
    Explanations

    terms related to loss, injury, and consequences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.10
     Ñıке
    -0.08
    æīĢæľī
    -0.07
    apus
    -0.07
    bih
    -0.07
    .SDK
    -0.07
    hangi
    -0.07
    rame
    -0.07
    omor
    -0.07
    elix
    -0.07
    POSITIVE LOGITS
     or
    0.14
     either
    0.12
     eller
    0.10
     hoặc
    0.09
     или
    0.09
     throughout
    0.09
    æĪĸ
    0.09
     themselves
    0.09
     oder
    0.09
    æĪĸèĢħ
    0.09
    Act Density 0.058%

    No Known Activations