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

    Neuronpedia

    INDEX
    Explanations

    quantitative expressions indicating large amounts or counts of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nÃło
    -0.16
    ypo
    -0.15
     stuff
    -0.15
     ones
    -0.15
    eh
    -0.15
    alace
    -0.14
    ops
    -0.14
     hierarchy
    -0.14
    oom
    -0.14
    OrDefault
    -0.14
    POSITIVE LOGITS
     upon
    0.20
     of
    0.17
    fold
    0.17
    atta
    0.16
    ToMany
    0.15
     Upon
    0.15
    zm
    0.15
    FOX
    0.15
    -fold
    0.15
    heets
    0.15
    Act Density 0.027%

    No Known Activations