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

    Neuronpedia

    INDEX
    Explanations

    verbs related to making decisions or taking actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express intentions or goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Else
    -0.63
     Canary
    -0.62
     Mens
    -0.61
     Relief
    -0.61
     Pak
    -0.61
     Appropriations
    -0.58
    Plus
    -0.58
     Cosponsors
    -0.58
     casualty
    -0.57
    afety
    -0.57
    POSITIVE LOGITS
     accomplish
    1.15
     emulate
    1.08
     achieve
    1.06
     eradicate
    0.91
     avoid
    0.90
     eliminate
    0.90
     attain
    0.86
     solve
    0.86
     pursue
    0.85
     improve
    0.85
    Act Density 0.123%

    No Known Activations