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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "different"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Calendar
    -0.61
     Wiki
    -0.60
     Couch
    -0.58
     mutual
    -0.58
    ãĤ§
    -0.57
     Advisory
    -0.56
     boards
    -0.56
     smiles
    -0.56
    wiki
    -0.56
     Beans
    -0.55
    POSITIVE LOGITS
    iating
    1.34
    iates
    1.03
    iator
    0.96
    ĸļ
    0.91
    iated
    0.90
    iable
    0.89
     than
    0.89
     whatsoever
    0.88
    ials
    0.85
    worldly
    0.82
    Act Density 0.012%

    No Known Activations