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

    Neuronpedia

    INDEX
    Explanations

    elements of narrative uncertainty and causality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gency
    -0.18
    оÑĤе
    -0.16
    odb
    -0.15
    é¹
    -0.15
    orks
    -0.15
    aginator
    -0.14
    reau
    -0.14
    виÑĩай
    -0.14
    ÏĢοÏħ
    -0.14
    atsby
    -0.14
    POSITIVE LOGITS
    orate
    0.15
     Virgin
    0.15
    o
    0.15
     Ore
    0.15
     soon
    0.15
    ubble
    0.15
     Pe
    0.15
     eventually
    0.15
     loud
    0.14
     Craft
    0.14
    Act Density 0.177%

    No Known Activations