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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "Tag" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idon
    -0.18
    erre
    -0.18
    icer
    -0.15
    agrams
    -0.15
    iser
    -0.15
    oust
    -0.14
    avier
    -0.14
    eren
    -0.14
    ester
    -0.14
    imest
    -0.14
    POSITIVE LOGITS
    alog
    0.16
    ged
    0.16
     Malone
    0.14
    lesen
    0.14
    ucci
    0.14
    879
    0.14
    GED
    0.14
    058
    0.14
    rchive
    0.14
    aji
    0.13
    Act Density 0.013%

    No Known Activations