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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to fraud and scams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abbr
    -0.14
    untu
    -0.14
     кÑĢиÑĤ
    -0.14
    ntag
    -0.14
    æ´
    -0.14
    óg
    -0.14
    :NS
    -0.14
     veto
    -0.14
     sprink
    -0.13
    /Graphics
    -0.13
    POSITIVE LOGITS
     scam
    0.44
     scams
    0.43
    fra
    0.40
     fraud
    0.39
    Fra
    0.39
     Pon
    0.39
     rip
    0.36
     Fra
    0.35
     schemes
    0.35
     scheme
    0.35
    Act Density 0.300%

    No Known Activations