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

    Neuronpedia

    INDEX
    Explanations

    references to media networks and news programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.66
     gynhyrchwyd
    -0.56
    省市镇
    -0.53
    們
    -0.48
    rind
    -0.47
    们
    -0.46
    们的
    -0.46
     nào
    -0.46
     alike
    -0.45
    ךְ
    -0.45
    POSITIVE LOGITS
     appunto
    1.15
     genoemd
    1.05
     genannt
    0.80
     refiri
    0.71
    と呼ばれる
    0.70
    と呼ば
    0.68
    SharedDtor
    0.67
    といいます
    0.64
    AndEndTag
    0.62
    which
    0.61
    Act Density 0.575%

    No Known Activations