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

    Neuronpedia

    INDEX
    Explanations

    phrases related to suspicious activities or security risks, particularly in the context of financial transactions and cybersecurity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     apologised
    -0.64
    laga
    -0.59
    lappe
    -0.58
     apologized
    -0.56
    capsulation
    -0.53
     apologies
    -0.52
     apologizing
    -0.51
    colgroup
    -0.51
    ध्य
    -0.51
     apolog
    -0.50
    POSITIVE LOGITS
     suspicious
    0.83
    :+:
    0.68
     suspicion
    0.67
    NameInMap
    0.67
    Suspicious
    0.67
     sospe
    0.64
    UnusedPrivate
    0.61
     detection
    0.60
     detecting
    0.58
    enumii
    0.58
    Act Density 0.569%

    No Known Activations