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

    Neuronpedia

    INDEX
    Explanations

    references to choice and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     crackdown
    -0.60
    TestingModule
    -0.57
    aria
    -0.53
    paramref
    -0.52
     Genu
    -0.52
     popularity
    -0.51
     forbade
    -0.51
    essi
    -0.51
     early
    -0.51
     pity
    -0.51
    POSITIVE LOGITS
     interag
    0.92
     interactions
    0.91
     interaction
    0.84
     interact
    0.84
     interacting
    0.82
     interacts
    0.80
     Interactions
    0.79
    Interactions
    0.76
     billions
    0.73
     shaped
    0.72
    Act Density 0.481%

    No Known Activations