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

    Neuronpedia

    INDEX
    Explanations

    references to characters, specifically those related to children, family, and authority figures in various contexts

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

    male persons or individuals being referred to or described in narrative contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     its
    -0.69
     itself
    -0.58
     Оно
    -0.52
    它的
    -0.49
     оно
    -0.47
    Its
    -0.47
     Its
    -0.46
    它
    -0.45
    itself
    -0.45
    its
    -0.41
    POSITIVE LOGITS
     who
    1.02
    AddTagHelper
    0.91
     whose
    0.88
    tanleria
    0.80
     whofe
    0.79
     whom
    0.77
     whoſe
    0.76
    whose
    0.76
     quien
    0.73
    elemField
    0.71
    Act Density 0.641%

    No Known Activations