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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Last" and punctuation marks

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    G
    -0.52
     
    -0.50
     sidang
    -0.47
     Dillon
    -0.47
     ulei
    -0.46
    '
    -0.45
    sei
    -0.44
     giri
    -0.44
    I
    -0.44
     vieja
    -0.44
    POSITIVE LOGITS
    AddTagHelper
    1.15
     للمعارف
    0.96
     Roskov
    0.96
     nakalista
    0.95
    LookAnd
    0.85
    :✨
    0.82
    RegressionTest
    0.82
    ValueGeneration
    0.81
    dolu
    0.79
     protoimpl
    0.79
    Act Density 0.000%

    No Known Activations