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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant life changes and turmoil

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oux
    -0.19
    allet
    -0.16
    vig
    -0.15
    umann
    -0.15
    orne
    -0.15
    -INF
    -0.14
    تدÙī
    -0.14
    igne
    -0.14
    rych
    -0.14
    owl
    -0.14
    POSITIVE LOGITS
     lives
    0.19
     world
    0.19
     life
    0.18
     worlds
    0.17
     CHANGE
    0.16
    iske
    0.16
     everything
    0.16
     priorities
    0.15
     tang
    0.15
     changed
    0.15
    Act Density 0.099%

    No Known Activations