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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial transactions and advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     folks
    -0.25
     substantive
    -0.23
     assistance
    -0.23
     aspects
    -0.22
     assessment
    -0.22
     ongoing
    -0.21
     longstanding
    -0.21
     subsequent
    -0.21
     standout
    -0.21
     requisite
    -0.20
    POSITIVE LOGITS
     famous
    0.33
     completely
    0.29
     stupid
    0.23
     correct
    0.22
     forbidden
    0.22
     corrupted
    0.22
     explicitly
    0.20
     immortal
    0.20
     literally
    0.20
     absolutely
    0.20
    Act Density 0.078%

    No Known Activations