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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the word 'including' and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sko
    -0.15
    nodoc
    -0.15
     (~(
    -0.14
    forma
    -0.14
    324
    -0.14
    odos
    -0.14
    fen
    -0.14
    uda
    -0.14
     Scarlet
    -0.14
    onen
    -0.14
    POSITIVE LOGITS
    골
    0.17
    rawer
    0.14
     fol
    0.14
    ìłĪ
    0.14
    輯
    0.13
     Ost
    0.13
    .anchor
    0.13
     Mini
    0.13
    ipp
    0.13
     gen
    0.13
    Act Density 0.041%

    No Known Activations