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

    Neuronpedia

    INDEX
    Explanations

    terms related to the impact or effect on various subjects, particularly in contexts that indicate a change or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     complètes
    -0.56
    айт
    -0.55
    торая
    -0.54
    is
    -0.52
    i
    -0.52
    нутрен
    -0.51
     высоким
    -0.51
    x
    -0.51
    a
    -0.50
    tc
    -0.50
    POSITIVE LOGITS
     influencing
    1.41
     affecting
    1.41
     affects
    1.34
     affect
    1.33
     influences
    1.30
     Affecting
    1.30
     impacting
    1.30
    InjectAttribute
    1.30
     AFFECT
    1.29
     impacts
    1.29
    Act Density 0.434%

    No Known Activations