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

    Neuronpedia

    INDEX
    Explanations

    phrases that relate to emotional responses and feelings of anxiety or discomfort

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

    Followed by "me"

    np_acts-logits-general · gemini-2.0-flash

    me, them, us

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    they
    -0.87
    THEY
    -0.75
    his
    -0.70
    them
    -0.69
    you
    -0.69
     You
    -0.67
    YOU
    -0.67
    we
    -0.66
     They
    -0.66
     We
    -0.63
    POSITIVE LOGITS
     resourceCulture
    1.17
     tartalomajánló
    1.15
    AndEndTag
    1.15
     autorytatywna
    1.15
     للاسماء
    1.14
    tagHelperRunner
    1.14
    ########.
    1.14
     estekak
    1.11
    TagMode
    1.11
    ReusableCell
    1.08
    Act Density 0.170%

    No Known Activations