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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with legal terminology and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     the
    -0.59
    ,
    -0.58
     to
    -0.55
     its
    -0.47
     a
    -0.47
     باخ
    -0.46
     for
    -0.45
     in
    -0.45
     Савезне
    -0.44
    脚注の使い方
    -0.44
    POSITIVE LOGITS
    ↵↵
    1.40
    <eos>
    0.96
    ')){
    0.82
    ']").
    0.79
    .’”
    0.78
    }\]
    0.77
    )){
    0.77
    ]='\
    0.76
    ")){
    0.76
    Rüyada
    0.76
    Act Density 1.353%

    No Known Activations