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

    Neuronpedia

    INDEX
    Explanations

    mentions of size or scale

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "larger" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SR
    -0.80
    elf
    -0.79
    onso
    -0.76
    DVD
    -0.75
    ILLE
    -0.74
    ICE
    -0.72
     Called
    -0.72
    me
    -0.72
    Blade
    -0.72
    EP
    -0.71
    POSITIVE LOGITS
     sized
    1.10
     eleph
    1.03
     intestine
    1.03
     than
    0.98
     quantities
    0.91
    than
    0.88
     contiguous
    0.86
     diameter
    0.84
     proportions
    0.83
     Than
    0.82
    Act Density 0.011%

    No Known Activations