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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "after" and its variations, indicating a focus on temporal transitions or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     honom
    -0.50
    SceneManagement
    -0.41
     henne
    -0.39
     ihn
    -0.37
     hatta
    -0.36
     lui
    -0.35
     Вам
    -0.34
     incorporar
    -0.34
     Yourself
    -0.34
    InjectAttribute
    -0.33
    POSITIVE LOGITS
     they
    1.04
     she
    0.76
     we
    0.74
     he
    0.71
     CURIAM
    0.68
     arriving
    0.67
     receiving
    0.67
     failing
    0.65
     realizing
    0.64
     realising
    0.62
    Act Density 0.241%

    No Known Activations