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

    Neuronpedia

    INDEX
    Explanations

    mentions of topics related to digital rights and content management

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

    Followed by certain punctuation (, et) or function words

    np_acts-logits-general · gemini-2.0-flash

    lists, headers, code, or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.80
     purpoſe
    -0.71
     chrétien
    -0.68
     îna
    -0.68
     houſe
    -0.66
     themſelves
    -0.64
     față
    -0.63
     Theſe
    -0.63
     malheureux
    -0.62
     Juifs
    -0.61
    POSITIVE LOGITS
     delights
    0.70
     ideal
    0.69
     delight
    0.68
     charming
    0.65
     lovely
    0.61
     unforgettable
    0.61
    tagext
    0.59
     exquisite
    0.59
     colourful
    0.58
     surprises
    0.58
    Act Density 0.083%

    No Known Activations