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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or exclamation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĭ
    -0.17
    ected
    -0.17
    oleon
    -0.16
    ibt
    -0.16
    encer
    -0.15
    icip
    -0.15
    uptools
    -0.15
    elyn
    -0.15
    ÄĻk
    -0.15
    oders
    -0.14
    POSITIVE LOGITS
    mega
    0.19
    ana
    0.19
    mage
    0.18
     snap
    0.18
    irsch
    0.18
     boy
    0.18
    annes
    0.18
    ysical
    0.18
    iggins
    0.17
    rens
    0.17
    Act Density 0.018%

    No Known Activations