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

    Neuronpedia

    INDEX
    Explanations

    references to sin and wrongdoing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pooling
    -0.16
    लब
    -0.15
    ounder
    -0.15
     Redistributions
    -0.15
    å¾ħ
    -0.14
    便
    -0.14
    anford
    -0.14
    енÑĤ
    -0.14
    _pes
    -0.14
    icense
    -0.13
    POSITIVE LOGITS
    aji
    0.16
    agt
    0.14
    gle
    0.14
    ably
    0.14
    fully
    0.14
    gi
    0.14
     Whe
    0.14
    _runtime
    0.14
    mac
    0.14
    ified
    0.13
    Act Density 0.009%

    No Known Activations