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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships between various ideas or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.61
    msgTypes
    -0.59
    ssaint
    -0.55
    معلومات
    -0.53
     대한
    -0.52
     Оно
    -0.51
     dass
    -0.51
     weren
    -0.50
    ₂+
    -0.49
    gó
    -0.48
    POSITIVE LOGITS
     perhaps
    1.26
     ultimately
    1.17
    perhaps
    1.16
     possibly
    1.15
     sometimes
    1.09
     eventually
    1.07
    possibly
    1.06
     consequently
    1.05
     preferably
    1.04
     eventualmente
    1.04
    Act Density 0.309%

    No Known Activations