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

    Neuronpedia

    INDEX
    Explanations

    phrases related to names and naming in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [/
    -0.15
     Disclaimer
    -0.15
    icensed
    -0.15
    altung
    -0.14
    jang
    -0.13
    .qq
    -0.13
    isyon
    -0.13
     ÑĩÑĥж
    -0.12
    weet
    -0.12
    illos
    -0.12
    POSITIVE LOGITS
     named
    0.69
     name
    0.61
    named
    0.61
     Named
    0.56
    Named
    0.49
     naming
    0.48
     names
    0.46
    name
    0.46
    -name
    0.44
    åIJįåŃĹ
    0.44
    Act Density 0.295%

    No Known Activations