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

    Neuronpedia

    INDEX
    Explanations

    phrases and questions centered around opinions and thoughts

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

    asking for opinion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.59
    ंदीखरीदारी
    -0.50
    astify
    -0.48
     оригіналу
    -0.47
     estekak
    -0.47
     Roskov
    -0.46
    Diweddarwch
    -0.46
    mobileqq
    -0.46
     tartalomajánló
    -0.45
     esclavos
    -0.45
    POSITIVE LOGITS
     think
    0.63
    opinion
    0.58
     opinion
    0.58
     Opinion
    0.53
    Opinion
    0.50
     imagin
    0.50
    think
    0.50
     opinions
    0.49
     Critique
    0.48
     proportion
    0.47
    Act Density 0.008%

    No Known Activations