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

    Neuronpedia

    INDEX
    Explanations

    indicators of abundance or excess

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

    Comparative adjectives after "much", "more", "even", or "lot"

    np_acts-logits-general · gemini-2.0-flash

    intensifier followed by comparative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -1.10
     itſelf
    -1.09
    ſelf
    -1.06
     ſtate
    -1.05
     purpoſe
    -1.00
     houſe
    -0.99
     Monfieur
    -0.99
     ſche
    -0.98
     themſelves
    -0.97
     pleaſure
    -0.97
    POSITIVE LOGITS
     dir
    0.86
     bu
    0.82
     friend
    0.78
     sc
    0.78
     nas
    0.75
     bra
    0.75
     cra
    0.74
     s
    0.70
     ne
    0.68
     ug
    0.68
    Act Density 0.223%

    No Known Activations