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

    Neuronpedia

    INDEX
    Explanations

    expressions of disbelief or astonishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uada
    -0.16
    aux
    -0.15
    048
    -0.15
    βε
    -0.14
    _FF
    -0.14
    è¾¼
    -0.14
    lamaz
    -0.14
     ä»Ĭ
    -0.14
     partial
    -0.14
    εί
    -0.14
    POSITIVE LOGITS
    heits
    0.16
     tie
    0.15
    ulse
    0.15
    uhl
    0.15
    Marshal
    0.15
    691
    0.14
     Foster
    0.14
     anyone
    0.14
     Tie
    0.14
    waters
    0.14
    Act Density 0.098%

    No Known Activations