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

    Neuronpedia

    INDEX
    Explanations

    mentions of personal feelings and experiences related to relationships

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

    Follows auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    regularly or frequently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     חיצוניים
    -0.56
     vaik
    -0.51
    ropriate
    -0.51
    ")==
    -0.50
    på
    -0.50
    rump
    -0.49
    umumkan
    -0.49
    ponible
    -0.48
    nictwa
    -0.48
     autorytatywna
    -0.47
    POSITIVE LOGITS
     regularly
    0.98
     consistently
    0.96
    每次
    0.93
    毎回
    0.92
     frequently
    0.91
     occasionally
    0.90
     sering
    0.88
     frequency
    0.86
    经常
    0.86
    經常
    0.85
    Act Density 0.602%

    No Known Activations