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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the word "of" and its repeated occurrences in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cards
    -0.85
    aughters
    -0.80
    pointers
    -0.78
    rants
    -0.77
     cleaners
    -0.76
    holes
    -0.74
    pots
    -0.74
    members
    -0.73
    chairs
    -0.73
     cards
    -0.73
    POSITIVE LOGITS
     southeastern
    0.78
     southwestern
    0.76
     misinformation
    0.74
     southern
    0.69
     conversation
    0.67
     Europe
    0.67
     northwestern
    0.67
     groundwork
    0.66
     southeast
    0.64
     coastline
    0.64
    Act Density 0.120%

    No Known Activations