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

    Neuronpedia

    INDEX
    Explanations

    features related to product durability and eco-friendliness

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

    describing positive qualities

    np_acts-logits-general · gemini-2.0-flash

    qualities and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     것이다
    -0.79
     EconPapers
    -0.74
    GEBURTSDATUM
    -0.71
     Efq
    -0.70
    Autoritní
    -0.67
     okuyayım
    -0.66
    RTGC
    -0.66
    '])){
    -0.66
    AndEndTag
    -0.66
    ressee
    -0.65
    POSITIVE LOGITS
    unlike
    1.05
     unlike
    0.99
     thanks
    0.97
     compared
    0.88
     graças
    0.85
     grazie
    0.83
     grâce
    0.82
     even
    0.79
     благодаря
    0.78
    even
    0.78
    Act Density 0.310%

    No Known Activations