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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of marking or notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    梯
    -0.18
    archy
    -0.17
    ominator
    -0.16
    è¦
    -0.15
    \FrameworkBundle
    -0.15
    ī
    -0.15
    Ïįν
    -0.15
    ctions
    -0.15
    823
    -0.14
    Äįet
    -0.14
    POSITIVE LOGITS
    edly
    0.29
    eting
    0.28
    etable
    0.25
    eted
    0.25
    down
    0.24
    sm
    0.24
    eters
    0.24
    ups
    0.24
    places
    0.22
    ansas
    0.21
    Act Density 0.062%

    No Known Activations