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

    Neuronpedia

    INDEX
    Explanations

    mentions of governmental regulations and technological advancements

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to social and community awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nope
    -0.80
     dummy
    -0.68
    pure
    -0.66
    Legend
    -0.64
    killer
    -0.64
     Stones
    -0.64
    Yep
    -0.64
    Boo
    -0.64
    Exit
    -0.63
     Vanilla
    -0.63
    POSITIVE LOGITS
     grappling
    1.20
     grapp
    1.16
     grapple
    1.14
     acutely
    1.12
     urgently
    1.08
     need
    1.02
     increasingly
    1.02
     sensit
    0.99
     challenges
    0.96
     strive
    0.96
    Act Density 0.517%

    No Known Activations