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

    Neuronpedia

    INDEX
    Explanations

    references to assembly-related terminology and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.93
     noDo
    -0.89
    RetentionPolicy
    -0.88
     propOrder
    -0.87
    OrNil
    -0.85
     Yorke
    -0.83
     الرياضيه
    -0.83
    +:+
    -0.82
     Crusoe
    -0.81
    rdoba
    -0.80
    POSITIVE LOGITS
     assembly
    2.08
     Assembly
    2.01
    Assembly
    1.84
    assemb
    1.81
     ASSEMBLY
    1.77
     assemblies
    1.74
    assembly
    1.71
     assemb
    1.70
    Assemb
    1.64
     assemble
    1.61
    Act Density 0.059%

    No Known Activations