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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or subjects in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    indicating possession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     corso
    -0.42
     tirage
    -0.42
     parlant
    -0.42
     itſelf
    -0.41
     quidem
    -0.40
    吒
    -0.38
     jura
    -0.38
     ſtand
    -0.37
    listData
    -0.37
     raso
    -0.37
    POSITIVE LOGITS
     whose
    1.28
    whose
    1.27
     Whose
    1.13
    Whose
    1.13
     cuya
    0.94
     cuyo
    0.94
     cuja
    0.93
     cujo
    0.88
     whofe
    0.88
     cuyas
    0.88
    Act Density 0.008%

    No Known Activations