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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurements or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.71
     MA
    -0.66
     getM
    -0.66
     MEN
    -0.62
     M
    -0.60
     Ma
    -0.60
    UnusedPrivate
    -0.59
     М
    -0.59
    +#+#
    -0.58
     МА
    -0.58
    POSITIVE LOGITS
    m
    1.17
    ming
    1.11
    mi
    1.09
    mer
    1.06
    mm
    1.05
    my
    1.04
    ms
    1.04
    mas
    1.04
    min
    1.01
    mers
    1.01
    Act Density 0.555%

    No Known Activations