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

    Neuronpedia

    INDEX
    Explanations

    references to ownership or relationships indicated by the word "whose"

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

    shows possession or relation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GUILayout
    -0.36
     ſtate
    -0.35
    度
    -0.34
    上
    -0.34
     Fontana
    -0.34
    l
    -0.33
     purpoſe
    -0.33
     dedans
    -0.33
    Điều
    -0.32
     reti
    -0.32
    POSITIVE LOGITS
     whose
    1.41
    whose
    1.31
     Whose
    1.20
    Whose
    1.19
     whofe
    1.12
     cuja
    1.02
     cuyo
    0.99
     cuya
    0.98
     whoſe
    0.97
     cuyos
    0.95
    Act Density 0.006%

    No Known Activations