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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and return statements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aid
    -0.15
     Helen
    -0.15
    rew
    -0.15
    taÅŁ
    -0.15
     Seymour
    -0.15
    he
    -0.14
    sum
    -0.14
    ted
    -0.14
    vir
    -0.14
    udded
    -0.14
    POSITIVE LOGITS
    loadModel
    0.16
    519
    0.15
    724
    0.15
    bomb
    0.15
    byss
    0.14
    lé
    0.14
    JsonValue
    0.14
    تÙĪر
    0.14
    itra
    0.14
    abase
    0.14
    Act Density 0.005%

    No Known Activations