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

    Neuronpedia

    INDEX
    Explanations

    references to specific names or terms associated with identity, particularly personal or cultural identification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xeb
    -0.17
    ivan
    -0.17
    icy
    -0.15
    overn
    -0.15
    483
    -0.15
     winds
    -0.14
    aar
    -0.14
    ewn
    -0.14
    buie
    -0.14
    haps
    -0.14
    POSITIVE LOGITS
     Fi
    0.18
    patrick
    0.16
    ancial
    0.16
    tering
    0.16
    orent
    0.15
    gerald
    0.15
    afa
    0.15
    zelf
    0.15
    kers
    0.15
    OLL
    0.14
    Act Density 0.031%

    No Known Activations