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

    Neuronpedia

    INDEX
    Explanations

    specific key terms related to data structures and their relationships in various contexts

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

    possessive or relating to plural nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     its
    -0.84
    Its
    -0.69
    它的
    -0.66
     оно
    -0.65
     Its
    -0.64
    Geplaatst
    -0.61
     Оно
    -0.59
    它
    -0.57
    '])){
    -0.54
    its
    -0.53
    POSITIVE LOGITS
     themselves
    1.30
    themselves
    1.22
     themſelves
    0.95
     Their
    0.85
    Their
    0.84
     their
    0.79
    their
    0.77
     själva
    0.75
     olduk
    0.72
     loro
    0.69
    Act Density 0.269%

    No Known Activations