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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming concepts and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ActionCreators
    -0.35
    astify
    -0.34
     consecu
    -0.33
     feroit
    -0.32
     guerres
    -0.32
     Meksi
    -0.32
     sayur
    -0.31
     llena
    -0.31
    uevos
    -0.31
    Vanjske
    -0.30
    POSITIVE LOGITS
     universal
    1.02
    universal
    0.98
     универса
    0.84
     universality
    0.82
    Universal
    0.81
     Universal
    0.79
     universale
    0.79
     UNIVERSAL
    0.77
     universally
    0.74
     uniwers
    0.73
    Act Density 0.836%

    No Known Activations