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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns

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

    pronouns followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ainfi
    -0.66
     pleaſure
    -0.63
     houſe
    -0.59
     NSCoder
    -0.58
     auroit
    -0.57
    مصادر
    -0.52
     CanadaChoose
    -0.52
     contextLoads
    -0.52
     Normdatei
    -0.51
    enumi
    -0.49
    POSITIVE LOGITS
    richTextPanel
    0.36
    二是
    0.35
    sel
    0.35
    si
    0.34
    fvar
    0.34
    sy
    0.33
    sed
    0.33
    ChildScrollView
    0.32
    ty
    0.32
    bi
    0.32
    Act Density 0.132%

    No Known Activations