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

    Neuronpedia

    INDEX
    Explanations

    statements expressing beliefs and opinions

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

    Sentences starting with "We"

    np_acts-logits-general · gemini-2.0-flash

    We or our followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conmigo
    -1.12
     comigo
    -1.03
     mnie
    -0.82
     me
    -0.77
    私に
    -0.76
     asegurarse
    -0.74
     мне
    -0.72
     मुझे
    -0.71
    ผม
    -0.71
     мной
    -0.69
    POSITIVE LOGITS
     ourselves
    2.98
     our
    1.64
     можем
    1.38
    Our
    1.26
     Our
    1.25
    our
    1.23
     we
    1.23
     знаем
    1.19
     We
    1.18
    我們的
    1.13
    Act Density 1.158%

    No Known Activations