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

    Neuronpedia

    INDEX
    Explanations

    names and relationships in personal narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gow
    -0.17
    adol
    -0.17
    atos
    -0.16
    orate
    -0.16
    iox
    -0.15
    akens
    -0.15
    illos
    -0.15
    icot
    -0.14
    ersh
    -0.14
     Bull
    -0.14
    POSITIVE LOGITS
     Grande
    0.46
     Ari
    0.43
    ARI
    0.28
    arian
    0.27
     Mac
    0.26
     MAC
    0.25
     Davidson
    0.25
    Mac
    0.24
     grande
    0.24
    MAC
    0.24
    Act Density 0.000%

    No Known Activations