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

    Neuronpedia

    INDEX
    Explanations

    variables or symbols used in mathematical notation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    الإنجليزية
    -0.84
    fjspx
    -0.72
     propOrder
    -0.71
    ngdoc
    -0.69
    resave
    -0.67
    expandindo
    -0.65
    ftagPool
    -0.65
    rrggbb
    -0.63
    Extinguishing
    -0.63
    下载附件
    -0.61
    POSITIVE LOGITS
    夷
    0.55
    iform
    0.54
    Misty
    0.54
     plano
    0.54
    Grüße
    0.53
    انيف
    0.50
     miel
    0.49
    viste
    0.49
     somewhere
    0.49
    orz
    0.49
    Act Density 0.006%

    No Known Activations