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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of famous individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orent
    -0.18
    -addon
    -0.17
    ly
    -0.15
    222
    -0.15
     æ°¸
    -0.14
    ivement
    -0.14
    ips
    -0.14
     exerc
    -0.14
    кÑĢа
    -0.14
    .createServer
    -0.14
    POSITIVE LOGITS
     Messi
    0.23
    ingleton
    0.17
     Richie
    0.16
    tb
    0.16
    θι
    0.16
    ÅĤe
    0.16
    opping
    0.15
     mess
    0.15
    اÙĬر
    0.14
    mess
    0.14
    Act Density 0.011%

    No Known Activations