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

    Neuronpedia

    INDEX
    Explanations

    references to catalog entries or listings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chart
    -0.16
    ield
    -0.16
    ifen
    -0.15
    bid
    -0.15
    itin
    -0.15
    ÑģÑı
    -0.15
    ials
    -0.14
    itung
    -0.14
    ities
    -0.14
    unning
    -0.14
    POSITIVE LOGITS
    ues
    0.34
    ue
    0.32
    ued
    0.27
    uer
    0.24
    uing
    0.24
    UE
    0.22
    ueue
    0.21
    ué
    0.20
     rais
    0.20
    /catalog
    0.19
    Act Density 0.004%

    No Known Activations