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

    Neuronpedia

    INDEX
    Explanations

    terms related to superlatives or high levels of a concept

    oai_token-act-pair · gpt-3.5-turbo

    references to volcanic activity and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     omission
    -0.87
    PLA
    -0.77
     Cly
    -0.69
    cember
    -0.61
     muted
    -0.61
    displayText
    -0.60
    gow
    -0.60
     distinguishing
    -0.60
     Lange
    -0.58
     bes
    -0.57
    POSITIVE LOGITS
    rencies
    0.97
    puters
    0.88
    ooters
    0.85
    anny
    0.85
    puting
    0.80
    opes
    0.77
    itions
    0.76
    uctor
    0.75
    olester
    0.74
    iolet
    0.74
    Act Density 0.073%

    No Known Activations