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

    Neuronpedia

    INDEX
    Explanations

    assert statements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fa
    -0.16
    泡
    -0.16
    agrams
    -0.16
    ãĥ¼ãĥª
    -0.16
    rick
    -0.15
    bell
    -0.15
    ucz
    -0.15
    λÏħ
    -0.15
    alian
    -0.15
    zend
    -0.14
    POSITIVE LOGITS
    ุ
    0.16
    ofile
    0.15
     verg
    0.15
     hypo
    0.14
    aper
    0.14
    éri
    0.14
     Gym
    0.14
    -Compatible
    0.13
    sit
    0.13
     counterpart
    0.13
    Act Density 0.040%

    No Known Activations