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

    Neuronpedia

    INDEX
    Explanations

    expressions of disbelief or surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Companion
    -0.17
    edad
    -0.16
    okies
    -0.15
    ÑĢиг
    -0.15
    Ùģت
    -0.15
    elman
    -0.14
    ovah
    -0.14
    oku
    -0.14
    aku
    -0.14
    abaj
    -0.14
    POSITIVE LOGITS
    dde
    0.17
     poll
    0.16
    polit
    0.15
    ampo
    0.15
    ire
    0.14
    uÅŁ
    0.14
     portion
    0.14
    alles
    0.14
    itta
    0.14
     dig
    0.14
    Act Density 0.155%

    No Known Activations