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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and their usage in phrases

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

    connecting words in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arşivlendi
    -0.67
    bootstrapcdn
    -0.63
     myſelf
    -0.63
    存于互联网档案馆
    -0.62
     EconPapers
    -0.61
     Houſe
    -0.61
     Majefty
    -0.61
    httphttps
    -0.60
     queſta
    -0.59
    Personensuche
    -0.57
    POSITIVE LOGITS
    /*
    0.43
    pop
    0.37
     Herr
    0.35
     quiera
    0.35
    /*
    0.35
    pl
    0.33
    les
    0.33
    ,
    0.33
    fn
    0.33
     –
    0.33
    Act Density 0.359%

    No Known Activations