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

    Neuronpedia

    INDEX
    Explanations

    patterns related to names and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acent
    -0.15
     lug
    -0.15
    lug
    -0.15
     dude
    -0.15
    erna
    -0.14
    creasing
    -0.14
     Stanton
    -0.14
    tember
    -0.14
    pedia
    -0.14
     Corner
    -0.14
    POSITIVE LOGITS
    haar
    0.17
    ÑĦек
    0.15
    격
    0.14
    icros
    0.14
    engin
    0.14
    .TestCheck
    0.14
    eyer
    0.14
    çĬ¶
    0.14
     IsActive
    0.13
    ãĤ¹ãĥ¬
    0.13
    Act Density 0.073%

    No Known Activations