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

    Neuronpedia

    INDEX
    Explanations

    sequences of special characters or formatting elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    affer
    -0.17
    enheim
    -0.15
    .loop
    -0.15
    plen
    -0.14
    pher
    -0.14
     rhet
    -0.14
    tent
    -0.14
    loff
    -0.14
     Highlander
    -0.14
    aman
    -0.14
    POSITIVE LOGITS
    cline
    0.20
    mult
    0.19
    row
    0.18
    mid
    0.16
    iasi
    0.16
    ForRow
    0.15
     row
    0.15
    iko
    0.15
     multic
    0.15
    osaur
    0.15
    Act Density 0.009%

    No Known Activations