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

    Neuronpedia

    INDEX
    Explanations

    short phrases or sentences with a high frequency of punctuation marks and potential indications of randomness

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical values or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     frontline
    -0.84
     orchestr
    -0.83
     payroll
    -0.81
     encomp
    -0.77
     dubbed
    -0.76
     displacement
    -0.76
     synerg
    -0.75
     offshore
    -0.74
     repatri
    -0.74
     negoti
    -0.73
    POSITIVE LOGITS
    Anyway
    1.45
    Reply
    1.38
    Advertisement
    1.37
    RAW
    1.30
    Advertisements
    1.30
    Then
    1.23
    Chapter
    1.21
    Trivia
    1.21
    Loading
    1.19
    When
    1.19
    Act Density 0.524%

    No Known Activations