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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly those related to places and names in Slovenian and Polish contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NOI
    -0.65
    :✨
    -0.59
    IUrlHelper
    -0.59
     Warden
    -0.58
    帖最后由
    -0.57
    simpleType
    -0.57
    addWidget
    -0.56
    twimg
    -0.56
     MainAxisSize
    -0.55
    readdir
    -0.55
    POSITIVE LOGITS
    sky
    0.62
     surla
    0.60
    ական
    0.56
    SKY
    0.53
     accompli
    0.53
    ская
    0.52
    ские
    0.52
    SK
    0.52
    ский
    0.52
    ske
    0.49
    Act Density 0.118%

    No Known Activations