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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the impact and effects of various actions and phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignet
    -0.16
    orado
    -0.16
    tridge
    -0.15
    emoc
    -0.15
    nelly
    -0.15
    ãĥ¼ãĥ³
    -0.15
    osate
    -0.14
    ritt
    -0.14
    åĪĹ
    -0.14
    fty
    -0.14
    POSITIVE LOGITS
    æݪ
    0.17
    crud
    0.15
    mere
    0.14
     Aim
    0.14
    103
    0.14
    .pay
    0.13
    Metric
    0.13
     Yok
    0.13
    ared
    0.13
    諸
    0.13
    Act Density 0.083%

    No Known Activations