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

    Neuronpedia

    INDEX
    Explanations

    terms related to capabilities and capacities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sandalias
    -0.39
     føl
    -0.39
     viagem
    -0.38
     agresión
    -0.38
     ordine
    -0.37
     embarazada
    -0.37
     nästa
    -0.37
     gömlek
    -0.36
     calcetines
    -0.36
     étape
    -0.35
    POSITIVE LOGITS
     capability
    1.20
     capacity
    1.16
     ability
    1.16
    capacity
    1.13
     Capability
    1.10
     Capacity
    1.07
     Ability
    1.05
     capabilities
    1.03
     Capabilities
    1.02
    capability
    1.02
    Act Density 0.125%

    No Known Activations