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

    Neuronpedia

    INDEX
    Explanations

    terms related to contrasting perspectives or actions within a certain context

    oai_token-act-pair · gpt-3.5-turbo

    references to societal issues and challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    engers
    -0.76
     Translation
    -0.69
     Cipher
    -0.65
     Explan
    -0.64
     Bulgar
    -0.64
    anche
    -0.64
     diagrams
    -0.63
    esses
    -0.63
     ensu
    -0.63
    lass
    -0.63
    POSITIVE LOGITS
     otherwise
    1.05
     previously
    0.94
     ordinarily
    0.90
     embattled
    0.89
     formerly
    0.88
     dormant
    0.88
     hitherto
    0.86
     sorely
    0.85
     stagnant
    0.83
     traditionally
    0.83
    Act Density 0.757%

    No Known Activations