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

    Neuronpedia

    INDEX
    Explanations

    mentions of service-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iary
    -0.85
    uran
    -0.83
    sty
    -0.71
    ean
    -0.70
    aundering
    -0.69
    sbm
    -0.68
    Filename
    -0.67
    berra
    -0.66
    ivil
    -0.65
    iaries
    -0.65
    POSITIVE LOGITS
     Provider
    1.04
     provider
    1.01
     providers
    0.96
     outage
    0.92
     Samurai
    0.80
     acad
    0.77
    ABLE
    0.76
     Employees
    0.75
    ability
    0.71
     rendered
    0.71
    Act Density 0.028%

    No Known Activations