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

    Neuronpedia

    INDEX
    Explanations

    content related to data security and protection measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uce
    -0.17
     Paid
    -0.15
    ington
    -0.15
    lington
    -0.15
    alam
    -0.14
    uf
    -0.14
    .onCreate
    -0.14
     ucfirst
    -0.14
     Division
    -0.14
    éné
    -0.14
    POSITIVE LOGITS
    rios
    0.14
    溫
    0.14
     ounces
    0.14
    íķ
    0.14
    uggle
    0.14
    lexical
    0.13
    DEF
    0.13
     Gould
    0.13
    tru
    0.13
    lesc
    0.13
    Act Density 0.174%

    No Known Activations