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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apg
    -0.16
    avana
    -0.15
     barrel
    -0.14
    ntag
    -0.14
     (
    -0.14
    LAS
    -0.13
     zab
    -0.13
    rob
    -0.13
     preliminary
    -0.13
     Gent
    -0.13
    POSITIVE LOGITS
    eln
    0.15
    illon
    0.15
    λÏį
    0.15
    ¯u
    0.15
     Haley
    0.15
     içi
    0.14
    reau
    0.14
    à¹Ģ
    0.14
    ãģ¼
    0.14
    .VK
    0.13
    Act Density 0.029%

    No Known Activations