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

    Neuronpedia

    INDEX
    Explanations

    terms related to measuring or quantifying the quantity of something

    oai_token-act-pair · gpt-3.5-turbo

    references to capacity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aida
    -0.83
    roma
    -0.74
    gnu
    -0.70
    scene
    -0.70
    enthal
    -0.69
     Ide
    -0.67
    atari
    -0.67
    ochet
    -0.67
    ĸļ
    -0.66
    isco
    -0.66
    POSITIVE LOGITS
     capacities
    1.35
     capacity
    1.24
     Capacity
    1.05
     utilization
    0.98
    capacity
    0.98
    acity
    0.79
     mismatch
    0.75
     capability
    0.74
     gaps
    0.74
     capabilities
    0.73
    Act Density 0.031%

    No Known Activations