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

    Neuronpedia

    INDEX
    Explanations

    atoms and particles related to physics and chemistry

    oai_token-act-pair · gpt-3.5-turbo

    terms related to electrons and atomic structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Delivery
    -0.78
    Honest
    -0.76
     experien
    -0.71
    ership
    -0.70
     Nights
    -0.70
    fare
    -0.67
    Recomm
    -0.66
     professionalism
    -0.65
    Rogue
    -0.65
     Inquisition
    -0.65
    POSITIVE LOGITS
     emitted
    1.16
    hips
    1.05
     formed
    1.01
    ynthesis
    1.00
    mith
    0.96
     protr
    0.92
     particles
    0.92
     forming
    0.92
     composing
    0.92
     embedded
    0.91
    Act Density 0.231%

    No Known Activations