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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss evidence and its interpretation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.09
    ########.
    -1.07
    脚注の使い方
    -1.03
     ujednoznacz
    -0.89
     itſelf
    -0.86
     contextLoads
    -0.85
     beginnetje
    -0.85
    出版年
    -0.84
    참고
    -0.82
    neſs
    -0.81
    POSITIVE LOGITS
    x
    0.40
     x
    0.38
     edile
    0.37
    ={()
    0.37
     mé
    0.37
    版
    0.36
    wes
    0.36
     true
    0.36
    <eos>
    0.36
     
    0.35
    Act Density 0.685%

    No Known Activations