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

    Neuronpedia

    INDEX
    Explanations

    references to community interactions and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zwar
    -0.15
    doing
    -0.15
    loo
    -0.14
     Doing
    -0.14
    Doing
    -0.14
    ä¹Łæĺ¯
    -0.14
     Become
    -0.14
    ÑĥÑĩа
    -0.14
    indle
    -0.14
    uku
    -0.14
    POSITIVE LOGITS
    aped
    0.18
     imposes
    0.17
     bring
    0.17
     impose
    0.17
     so
    0.16
     brings
    0.16
     poss
    0.16
     eng
    0.15
     pos
    0.15
     cultiv
    0.15
    Act Density 0.207%

    No Known Activations