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

    Neuronpedia

    INDEX
    Explanations

    references to heists or theft-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĶĭ
    -0.15
    elsen
    -0.14
     Dữ
    -0.14
    ruba
    -0.14
    Intermediate
    -0.14
    onnement
    -0.14
    onso
    -0.14
    ieres
    -0.14
     Swap
    -0.14
    apple
    -0.14
    POSITIVE LOGITS
     Bond
    0.17
    Bond
    0.16
    *pow
    0.15
     extra
    0.14
    andler
    0.14
    -Agent
    0.14
    Tier
    0.14
     agencies
    0.14
     Bass
    0.14
     recharge
    0.13
    Act Density 0.334%

    No Known Activations