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

    Neuronpedia

    INDEX
    Explanations

    terms related to using or handling features or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lira
    -0.53
     voltak
    -0.52
    Datuak
    -0.49
     Wrangler
    -0.48
     beszél
    -0.47
     társ
    -0.47
     OSError
    -0.46
    Ecotoxicity
    -0.44
    SpringRunner
    -0.44
     bagay
    -0.42
    POSITIVE LOGITS
    以
    1.45
     以
    1.23
    用
    1.22
     用
    0.98
    是以
    0.98
    由
    0.86
    用的
    0.80
    是用
    0.80
    可以用
    0.77
    الحياه
    0.77
    Act Density 0.183%

    No Known Activations