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

    Neuronpedia

    INDEX
    Explanations

    actions related to change or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MetroFramework
    -0.15
     Cord
    -0.14
     pozn
    -0.14
    riendly
    -0.14
    aret
    -0.13
    474
    -0.13
     Rig
    -0.13
    ReuseIdentifier
    -0.13
    osi
    -0.13
    uario
    -0.13
    POSITIVE LOGITS
     replaced
    0.25
    Instead
    0.21
     Instead
    0.20
     instead
    0.19
     altogether
    0.18
    _mv
    0.18
     вмеÑģÑĤ
    0.18
    æİī
    0.18
     replace
    0.17
     substituted
    0.17
    Act Density 0.262%

    No Known Activations