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

    Neuronpedia

    INDEX
    Explanations

    references to laws and regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to legal terms and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Narr
    -0.64
     Psal
    -0.61
     Glory
    -0.59
    Nob
    -0.59
     Zion
    -0.59
    Ô
    -0.58
     brightest
    -0.57
     Decl
    -0.57
     nutrit
    -0.57
     finest
    -0.56
    POSITIVE LOGITS
     applies
    0.79
     expires
    0.76
     rollout
    0.75
     violates
    0.73
     debuted
    0.72
     instituted
    0.72
     stemmed
    0.71
     extends
    0.71
     entails
    0.70
     championed
    0.66
    Act Density 0.348%

    No Known Activations