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

    Neuronpedia

    INDEX
    Explanations

    placeholders or markers in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    niosek
    -0.65
    rouvez
    -0.63
     asmen
    -0.61
    }{*}{
    -0.59
    jude
    -0.58
     Neve
    -0.56
    }{*}{}
    -0.56
     leña
    -0.56
    ConstraintLayout
    -0.56
     SDLK
    -0.55
    POSITIVE LOGITS
    
    2.75
    
    1.14
    
    1.06
    Datuak
    0.93
    
    0.93
    
    0.81
    Tikang
    0.79
    
    0.79
    期刊论文
    0.73
    脚注の使い方
    0.69
    Act Density 0.032%

    No Known Activations