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

    Neuronpedia

    INDEX
    Explanations

    words indicating significant changes or impactful transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    £½
    -0.17
    rica
    -0.16
    íĻĶ
    -0.16
     Král
    -0.15
    ieves
    -0.15
    otel
    -0.15
    Ñıк
    -0.14
     jac
    -0.14
    azel
    -0.14
    unfold
    -0.14
    POSITIVE LOGITS
     agent
    0.16
    agent
    0.16
    leta
    0.16
     çĽ
    0.15
    inator
    0.15
    /support
    0.15
    ILA
    0.15
    piece
    0.15
    Agent
    0.14
     Agent
    0.14
    Act Density 0.159%

    No Known Activations