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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "elements" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ught
    -0.18
    bie
    -0.17
    oke
    -0.16
    аж
    -0.16
    ably
    -0.16
    loff
    -0.15
    icker
    -0.15
     behalf
    -0.15
    erto
    -0.14
    ilion
    -0.14
    POSITIVE LOGITS
    alist
    0.22
    arily
    0.22
    ally
    0.19
    ary
    0.18
    arity
    0.18
     Ñģобой
    0.18
    wise
    0.18
    osate
    0.17
    ials
    0.17
    åij¨æľŁ
    0.17
    Act Density 0.087%

    No Known Activations