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

    Neuronpedia

    INDEX
    Explanations

    phrases related to candidates and their attributes, including identification and personal details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vulga
    -0.57
     choque
    -0.56
     denen
    -0.55
     fallu
    -0.50
     translators
    -0.47
     cosmopolitan
    -0.47
     midwives
    -0.46
     οι
    -0.46
    assable
    -0.45
     unseren
    -0.45
    POSITIVE LOGITS
     person
    0.99
    :✨
    0.78
     osoba
    0.78
     someone
    0.77
     pessoa
    0.77
     Someone
    0.76
     seseorang
    0.73
    someone
    0.72
    person
    0.71
    حوالہ
    0.71
    Act Density 0.475%

    No Known Activations