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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal introspection or deep understanding

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "inner workings" or "inner" aspects of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eday
    -0.83
    atoes
    -0.81
    enegger
    -0.78
    orthy
    -0.76
    HAHAHAHA
    -0.75
    essors
    -0.74
    enance
    -0.72
    ILLE
    -0.71
    netflix
    -0.70
    ORK
    -0.69
    POSITIVE LOGITS
     workings
    1.25
    most
    1.24
     combustion
    0.88
     sanct
    0.85
    ranean
    0.79
     circle
    0.75
     combust
    0.74
     thigh
    0.73
     Mongolia
    0.72
     turmoil
    0.72
    Act Density 0.021%

    No Known Activations