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

    Neuronpedia

    INDEX
    Explanations

    terms related to authority and organizational structures

    oai_token-act-pair · gpt-3.5-turbo

    abstract concepts related to identity and existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iday
    -0.85
    GER
    -0.81
    bern
    -0.80
    ger
    -0.77
    ergy
    -0.76
    izen
    -0.74
    iversity
    -0.74
    DER
    -0.74
    sonian
    -0.73
    OY
    -0.73
    POSITIVE LOGITS
     Peb
    0.97
    ously
    0.79
     quot
    0.79
    bringer
    0.78
     Principle
    0.77
    phal
    0.73
     quo
    0.73
     charms
    0.70
     Checks
    0.70
     Ratings
    0.68
    Act Density 0.153%

    No Known Activations