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

    Neuronpedia

    INDEX
    Explanations

    terms related to data processing and analysis techniques

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    att
    -0.51
    atten
    -0.50
    СТВ
    -0.48
    Users
    -0.46
     Sif
    -0.45
    ็ต
    -0.45
    decode
    -0.45
    users
    -0.44
    uttu
    -0.44
    ttp
    -0.44
    POSITIVE LOGITS
     ModelExpression
    0.76
    UnsafeEnabled
    0.56
     صوتيه
    0.56
    omeness
    0.55
     opérateur
    0.55
     demikian
    0.54
    ViewFeatures
    0.54
     nahilalakip
    0.54
    sizeCache
    0.54
     taxable
    0.53
    Act Density 0.641%

    No Known Activations