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

    Neuronpedia

    INDEX
    Explanations

    phrases related to human needs and societal issues surrounding healthcare and well-being

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

    followed by prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    their information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     people
    -0.74
     you
    -0.73
    you
    -0.70
    お客様
    -0.68
     players
    -0.66
     folks
    -0.65
     everyone
    -0.65
     ppl
    -0.65
     peoples
    -0.64
     everybody
    -0.64
    POSITIVE LOGITS
     themselves
    1.61
     their
    1.44
    themselves
    1.37
    their
    1.23
    Their
    1.13
     Their
    0.98
     ihres
    0.98
     leur
    0.95
     الرياضيه
    0.94
     kanilang
    0.94
    Act Density 1.069%

    No Known Activations