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

    Neuronpedia

    INDEX
    Explanations

    mentions of negative or critical comments or reports

    oai_token-act-pair · gpt-3.5-turbo

    references to societal issues and current events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     UNCLASSIFIED
    -0.90
    âĹ¼
    -0.71
    anwhile
    -0.70
     Azerb
    -0.68
     [*
    -0.67
     skelet
    -0.66
     pse
    -0.66
    ogether
    -0.66
    )."
    -0.65
     unden
    -0.63
    POSITIVE LOGITS
     âĢº
    0.84
     âĢİ
    0.69
     Belfast
    0.64
     Posted
    0.61
     Donald
    0.61
     Updated
    0.61
     Calculator
    0.60
     cryptocurrency
    0.59
     LEGO
    0.58
    âĢİ
    0.58
    Act Density 2.975%

    No Known Activations