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

    Neuronpedia

    INDEX
    Explanations

    references to user actions, obligations, and experiences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appable
    -0.15
    ozem
    -0.15
    eniable
    -0.14
    vrier
    -0.14
    ursal
    -0.14
    째
    -0.14
    antro
    -0.14
    anches
    -0.14
    undance
    -0.14
    hread
    -0.14
    POSITIVE LOGITS
     better
    0.78
    better
    0.66
     Better
    0.62
    Better
    0.58
     mejor
    0.47
     melhor
    0.44
     besser
    0.44
     лÑĥÑĩÑĪе
    0.39
     BET
    0.39
     mieux
    0.38
    Act Density 0.210%

    No Known Activations