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

    Neuronpedia

    INDEX
    Explanations

    references to identity and identification concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ook
    -0.18
    خاÙĨÙĩ
    -0.17
    оÑģÑĥд
    -0.16
    ese
    -0.16
    ond
    -0.16
    uter
    -0.15
    loe
    -0.15
    istry
    -0.15
    NC
    -0.14
    owing
    -0.14
    POSITIVE LOGITS
    ENTITY
    0.23
    entities
    0.20
     theft
    0.19
     Theft
    0.17
    /address
    0.15
    entifier
    0.15
    ifiant
    0.15
     marker
    0.15
    aho
    0.15
     twins
    0.15
    Act Density 0.035%

    No Known Activations