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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news reports or official statements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     stereotype
    -0.78
     glor
    -0.75
     ghetto
    -0.75
     gull
    -0.74
    Hum
    -0.73
    overty
    -0.70
    escent
    -0.70
     hated
    -0.68
     loneliness
    -0.68
     badass
    -0.68
    POSITIVE LOGITS
     timetable
    1.31
     pending
    1.27
     negotiations
    1.25
     feasibility
    1.23
     preliminary
    1.18
     consultations
    1.17
     consultation
    1.13
     finalized
    1.11
     discussions
    1.10
     deliberations
    1.10
    Act Density 6.032%

    No Known Activations