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

    Neuronpedia

    INDEX
    Explanations

    words related to activities or actions that involve force or destruction

    oai_token-act-pair · gpt-3.5-turbo

    references to fictional characters and titles in storytelling contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -1.04
    aution
    -0.93
    ials
    -0.92
     carbohyd
    -0.90
    umbers
    -0.89
    estate
    -0.84
    sembly
    -0.84
    icable
    -0.84
    ccording
    -0.83
    icating
    -0.83
    POSITIVE LOGITS
     Runner
    0.95
    Mania
    0.90
    lihood
    0.88
    Rate
    0.87
    Berry
    0.87
     Collection
    0.85
     Shack
    0.85
    IRO
    0.82
    Maker
    0.81
     Zone
    0.79
    Act Density 0.146%

    No Known Activations