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

    Neuronpedia

    INDEX
    Explanations

    specific objects and actions in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mechanisms, processes, and measures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ighed
    -0.81
    Rh
    -0.77
    cale
    -0.76
    Southern
    -0.75
    thens
    -0.75
    ORN
    -0.74
    terday
    -0.74
    Ô
    -0.74
    UG
    -0.73
    EG
    -0.72
    POSITIVE LOGITS
     kit
    0.80
     assemblies
    0.79
     modifiers
    0.78
     protector
    0.78
     deck
    0.77
     chamber
    0.77
     modifier
    0.77
     cube
    0.76
     pad
    0.74
     pool
    0.74
    Act Density 0.529%

    No Known Activations