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

    Neuronpedia

    INDEX
    Explanations

    expressions that convey surprise or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĥãĥĦ
    -0.18
    agma
    -0.15
    ôt
    -0.15
     lep
    -0.15
     Sil
    -0.15
    ss
    -0.14
    ssue
    -0.14
     fail
    -0.14
     issues
    -0.13
     Silk
    -0.13
    POSITIVE LOGITS
     Carlson
    0.16
    ghan
    0.16
    edes
    0.15
    /*č↵
    0.15
    iever
    0.15
    .GetBytes
    0.15
    lain
    0.15
    жив
    0.14
     NotSupportedException
    0.14
     crumbs
    0.14
    Act Density 0.009%

    No Known Activations