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

    Neuronpedia

    INDEX
    Explanations

    information or details related to technical products or services, such as contact information, product releases, and company updates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Transcript
    -0.79
    CHAT
    -0.76
     volunteering
    -0.76
     poem
    -0.75
     poems
    -0.75
     Investigator
    -0.74
    orget
    -0.74
     recount
    -0.73
     Volunte
    -0.73
     Volunteers
    -0.73
    POSITIVE LOGITS
     OEM
    1.06
     franchises
    1.06
     gimm
    1.05
     niche
    1.01
     sequels
    1.00
     innovate
    0.99
     lackluster
    0.99
     fanbase
    0.96
     ported
    0.96
     GPUs
    0.94
    Act Density 0.938%

    No Known Activations