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

    Neuronpedia

    INDEX
    Explanations

    references to sections within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufe
    -0.17
    rypto
    -0.16
    æľŁ
    -0.16
    usb
    -0.15
    ous
    -0.15
    joy
    -0.15
    velt
    -0.14
    bane
    -0.14
    anio
    -0.14
    è¾°
    -0.14
    POSITIVE LOGITS
    ally
    0.28
    naire
    0.27
    naires
    0.27
    als
    0.24
    nement
    0.21
    ality
    0.20
    alist
    0.20
    nal
    0.18
    .scalablytyped
    0.17
    ariat
    0.17
    Act Density 0.031%

    No Known Activations