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

    Neuronpedia

    INDEX
    Explanations

    words related to labeling and mislabeling in various contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Méri
    -0.57
     récomp
    -0.52
    undai
    -0.48
    viu
    -0.48
     OTTO
    -0.47
    essandro
    -0.47
    dirond
    -0.47
     Dorothea
    -0.47
     Piac
    -0.46
     réun
    -0.45
    POSITIVE LOGITS
     label
    1.56
     labels
    1.49
    label
    1.39
     Label
    1.38
     Labels
    1.33
    labels
    1.31
    Label
    1.29
     LABEL
    1.28
     labeling
    1.26
    LABEL
    1.22
    Act Density 0.078%

    No Known Activations