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

    Neuronpedia

    INDEX
    Explanations

    phrases related to methods or approaches

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to methods or approaches for problem-solving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     huh
    -0.78
     haha
    -0.77
     lol
    -0.69
    erker
    -0.69
    gie
    -0.68
    ô
    -0.67
     blah
    -0.63
    whatever
    -0.63
     doesnt
    -0.63
    verty
    -0.63
    POSITIVE LOGITS
     businesses
    1.05
     lawmakers
    1.02
     companies
    1.02
     employers
    1.02
     consumers
    1.02
     municipalities
    1.01
     insurers
    1.00
     automakers
    1.00
     governments
    1.00
     retailers
    0.99
    Act Density 0.506%

    No Known Activations