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

    Neuronpedia

    INDEX
    Explanations

    phrases related to official statements or communications

    oai_token-act-pair · gpt-3.5-turbo

    references to official statements or communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.70
    orest
    -0.70
    vantage
    -0.66
     idols
    -0.65
    onents
    -0.64
     orphans
    -0.62
    utters
    -0.62
    glomer
    -0.61
    haven
    -0.61
     detectors
    -0.61
    POSITIVE LOGITS
     interview
    1.39
     statement
    1.34
     affidavit
    1.31
     memo
    1.24
     remarks
    1.19
     email
    1.19
     memorandum
    1.17
     tweet
    1.16
     article
    1.14
     sermon
    1.13
    Act Density 0.207%

    No Known Activations