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

    Neuronpedia

    INDEX
    Explanations

    references to author names or citations within academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.17
    SPECTION
    -0.75
     become
    -0.67
    aughters
    -0.66
    CLUSIVE
    -0.66
    EMPT
    -0.66
     seriously
    -0.64
    PLANATION
    -0.63
     awakeFromNib
    -0.63
     brought
    -0.63
    POSITIVE LOGITS
     accla
    1.75
     Strukt
    1.64
     Kategor
    1.62
     „,
    1.54
     aen
    1.50
     §.
    1.48
     inev
    1.45
     effe
    1.45
     increa
    1.42
     nece
    1.41
    Act Density 0.108%

    No Known Activations