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

    Neuronpedia

    INDEX
    Explanations

    pronouns, particularly those referring to the first and second person

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

    things I you we

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.53
    bootstrapcdn
    -0.52
    InjectMocks
    -0.48
    BufferException
    -0.46
     varandra
    -0.46
     ब्रेकडाउन
    -0.45
     tudi
    -0.44
     nakalista
    -0.44
    jsxFileName
    -0.43
     föruts
    -0.43
    POSITIVE LOGITS
    tralight
    0.51
     grip
    0.50
     civi
    0.48
     Rik
    0.48
    +][
    0.47
     ?>>
    0.46
     Pik
    0.46
    Measure
    0.45
     Dino
    0.45
    tvguidetime
    0.45
    Act Density 0.046%

    No Known Activations