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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "knight" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ASF
    -0.17
    alf
    -0.15
    afs
    -0.14
    éĩı
    -0.14
    vers
    -0.14
     Credits
    -0.13
    hop
    -0.13
    nbsp
    -0.13
     sheet
    -0.13
    ATOR
    -0.13
    POSITIVE LOGITS
    boro
    0.15
    odia
    0.15
     sola
    0.15
     глÑı
    0.15
    esses
    0.15
    üven
    0.14
    ByExample
    0.14
    inned
    0.14
     absol
    0.14
    ẫu
    0.14
    Act Density 0.007%

    No Known Activations