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

    Neuronpedia

    INDEX
    Explanations

    terms related to unique attributes and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Arn
    -0.17
    burgh
    -0.16
    arest
    -0.15
    PIO
    -0.15
    Triple
    -0.15
    -thumbnails
    -0.15
    stown
    -0.15
     Wal
    -0.14
    gram
    -0.14
    wal
    -0.14
    POSITIVE LOGITS
    foon
    0.17
    zman
    0.16
     spreading
    0.15
    man
    0.15
     spreads
    0.15
    ndl
    0.15
    mana
    0.14
    curacy
    0.14
    оÑıн
    0.14
    roid
    0.14
    Act Density 0.030%

    No Known Activations