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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives and their variations

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

    comparative adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ambilan
    -0.41
    -0.41
    Access
    -0.40
    ąp
    -0.40
     access
    -0.39
    emény
    -0.38
     dimana
    -0.38
    ModelAttribute
    -0.37
     is
    -0.37
    behörde
    -0.37
    POSITIVE LOGITS
     greener
    0.98
     purer
    0.89
     healthier
    0.88
     fairer
    0.87
     paler
    0.85
     hotter
    0.85
     healthiest
    0.84
     smarter
    0.84
     smoother
    0.83
     funnier
    0.82
    Act Density 0.023%
    No Known Activations