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

    Neuronpedia

    INDEX
    Explanations

    terms that imply an increase in size, depth, or effectiveness

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

    comparative degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﴿
    -0.50
    岩
    -0.48
    ━
    -0.48
     Reif
    -0.47
    Field
    -0.46
     WIND
    -0.46
     Eich
    -0.45
     Feld
    -0.45
     Calvo
    -0.45
     Eck
    -0.45
    POSITIVE LOGITS
    faster
    0.91
    easier
    0.87
     greener
    0.81
    worse
    0.81
    Faster
    0.79
    longer
    0.79
     smarter
    0.79
     Smarter
    0.78
     healthier
    0.77
     denser
    0.77
    Act Density 0.050%

    No Known Activations