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

    Neuronpedia

    INDEX
    Explanations

    references to specific rows in a dataset or database

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ActionCreators
    -0.60
    providedIn
    -0.58
    SourceChecksum
    -0.56
    makta
    -0.54
    вгения
    -0.54
    Filmografie
    -0.52
    蔽
    -0.52
     fusca
    -0.51
     Signalez
    -0.51
    mensa
    -0.51
    POSITIVE LOGITS
     row
    4.87
     Row
    3.97
    row
    3.81
    Row
    3.67
     rows
    3.64
     ROW
    3.28
     Rows
    3.06
    ROW
    2.97
    rows
    2.58
    Rows
    2.50
    Act Density 0.050%

    No Known Activations