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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negative experiences or missed opportunities

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

    "Haven't" or "hasn't"

    np_acts-logits-general · gemini-2.0-flash

    have not experienced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ตาย
    -0.50
     autorytatywna
    -0.49
     Administrativna
    -0.48
    guiente
    -0.47
     Boek
    -0.42
    endpush
    -0.42
     חיצוניים
    -0.41
     skjø
    -0.41
     giyim
    -0.40
    expliquer
    -0.40
    POSITIVE LOGITS
     Has
    0.61
     has
    0.61
    Has
    0.59
    has
    0.58
     have
    0.57
     been
    0.57
     had
    0.57
    HasBeen
    0.56
     Hassel
    0.56
     Have
    0.53
    Act Density 0.097%

    No Known Activations