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

    Neuronpedia

    INDEX
    Explanations

    technical terms or instructions related to projects or objects

    oai_token-act-pair · gpt-3.5-turbo

    references to specific items or objects being described

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terness
    -0.76
    opus
    -0.76
    endment
    -0.75
    fecture
    -0.74
    Pa
    -0.70
    isconsin
    -0.70
    rontal
    -0.68
    itudinal
    -0.68
    irlf
    -0.68
    uncture
    -0.67
    POSITIVE LOGITS
     items
    1.08
     are
    1.06
     aren
    0.99
     include
    0.99
     types
    0.97
     codes
    0.94
     kinds
    0.94
     entities
    0.93
     entries
    0.93
     were
    0.91
    Act Density 0.118%

    No Known Activations