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

    Neuronpedia

    INDEX
    Explanations

    comprehensive guides or instructional content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phere
    -0.16
    umbledore
    -0.15
    LK
    -0.15
    ÑĢоÑĩ
    -0.15
     Johnston
    -0.15
    ombok
    -0.14
    adero
    -0.14
    лаж
    -0.14
    allery
    -0.13
    è¹
    -0.13
    POSITIVE LOGITS
     guide
    0.39
     Guide
    0.36
    -guide
    0.34
    _guide
    0.31
    guide
    0.29
     GUIDE
    0.28
    Guide
    0.28
     guides
    0.27
     Guides
    0.24
    uide
    0.23
    Act Density 0.069%

    No Known Activations