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

    Neuronpedia

    INDEX
    Explanations

    concepts related to alignment and connection in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ully
    -0.17
    elyn
    -0.16
    GINE
    -0.15
    خاÙĨÙĩ
    -0.15
    stown
    -0.15
    lyn
    -0.14
    oulouse
    -0.14
    andles
    -0.14
    ³
    -0.14
     Äijiá»ĥn
    -0.14
    POSITIVE LOGITS
    arity
    0.21
    ingly
    0.18
    amenti
    0.17
    atus
    0.16
     perfectly
    0.16
    ean
    0.15
    upiter
    0.15
    ing
    0.15
    rh
    0.15
    arser
    0.14
    Act Density 0.017%

    No Known Activations