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

    Neuronpedia

    INDEX
    Explanations

    phrases related to identity theft and fraud

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utral
    -0.16
    aily
    -0.15
    uchos
    -0.15
     Norton
    -0.14
    ản
    -0.14
    ãĥ¼ãĥ¬
    -0.14
    ån
    -0.14
     putas
    -0.14
     Davidson
    -0.14
    çIJ³
    -0.14
    POSITIVE LOGITS
    alker
    0.15
    fé
    0.15
     Gael
    0.14
     Riy
    0.14
    rix
    0.14
    ¸
    0.14
     |_|
    0.14
    entine
    0.13
    TIM
    0.13
    etz
    0.13
    Act Density 0.127%

    No Known Activations