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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives indicating size or degree

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

    Comparative adjectives (ends in "-er")

    np_acts-logits-general · gemini-2.0-flash

    comparative adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ━
    -0.54
     WIND
    -0.47
    ﴿
    -0.47
     Roll
    -0.46
    \]
    -0.46
    Field
    -0.45
    Anhalt
    -0.44
     roll
    -0.44
     photo
    -0.43
     Joachim
    -0.43
    POSITIVE LOGITS
    faster
    0.85
    easier
    0.84
     happier
    0.78
     fairer
    0.78
     betweenstory
    0.77
     healthier
    0.77
    longer
    0.77
    Faster
    0.76
     Smarter
    0.76
     greener
    0.76
    Act Density 0.216%

    No Known Activations