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

    Neuronpedia

    INDEX
    Explanations

    references to specific settings or configurations in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ainfi
    -0.91
     auroit
    -0.82
     feroit
    -0.81
     plufieurs
    -0.79
    MemoryWarning
    -0.79
    ſelf
    -0.79
     pouvoit
    -0.71
     eût
    -0.70
    存于互联网档案馆
    -0.70
     ſeine
    -0.70
    POSITIVE LOGITS
     setting
    0.67
     settings
    0.66
     Simmons
    0.47
    设置
    0.46
     enrollment
    0.46
     Victoria
    0.45
    /
    0.45
     frequent
    0.45
     Plaza
    0.44
     enrolled
    0.44
    Act Density 0.285%

    No Known Activations