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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scientific research, safety standards, and regulatory compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stones
    -0.17
     dis
    -0.15
    zew
    -0.15
    er
    -0.15
     categor
    -0.14
    Å¡t
    -0.14
    e
    -0.14
     outright
    -0.14
    945
    -0.14
    ring
    -0.14
    POSITIVE LOGITS
    lington
    0.18
    okino
    0.16
    ieux
    0.15
    ç©į
    0.15
     Shir
    0.14
    γÎŃν
    0.14
    æīķ
    0.14
    usra
    0.14
    <tag
    0.14
    DrawerToggle
    0.14
    Act Density 1.229%

    No Known Activations