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

    Neuronpedia

    INDEX
    Explanations

    references to various types of schemes, particularly those related to financial transactions and fraud

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    qq
    -0.47
    particles
    -0.45
     Garry
    -0.44
    Pron
    -0.44
    lid
    -0.44
     sof
    -0.43
     loving
    -0.43
    ty
    -0.43
    oren
    -0.42
    OrWhiteSpace
    -0.42
    POSITIVE LOGITS
     scheme
    4.83
     Scheme
    4.51
    scheme
    4.48
     schemes
    4.32
     Schemes
    4.22
     SCHEME
    4.20
    Scheme
    4.13
    schemes
    3.80
    Schemes
    3.49
    SCHEME
    3.44
    Act Density 0.078%

    No Known Activations