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

    Neuronpedia

    INDEX
    Explanations

    references to color

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aliana
    -1.87
    rapeut
    -1.62
    enig
    -1.56
     its
    -1.44
    uren
    -1.42
     centuries
    -1.38
     men
    -1.36
    ge
    -1.36
     adults
    -1.33
    ropol
    -1.33
    POSITIVE LOGITS
    stone
    1.88
    blind
    1.84
    less
    1.79
    plates
    1.74
    ston
    1.64
    stones
    1.56
    pile
    1.55
    REF
    1.55
    stick
    1.55
    finder
    1.54
    Act Density 0.406%

    No Known Activations