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

    Neuronpedia

    INDEX
    Explanations

    descriptions of simplicity and ease of use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mers
    -0.19
    ively
    -0.18
    ød
    -0.17
    piler
    -0.16
    /Branch
    -0.16
    pire
    -0.16
    lements
    -0.16
    .scalablytyped
    -0.16
    chers
    -0.15
    perature
    -0.15
    POSITIVE LOGITS
    going
    0.38
    -pe
    0.34
    -to
    0.31
     dÃłng
    0.31
    -going
    0.31
     bree
    0.27
     pe
    0.26
    /fast
    0.26
    -access
    0.23
    Jet
    0.22
    Act Density 0.057%

    No Known Activations