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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence structure markers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     которое
    -0.60
    which
    -0.55
     Asimismo
    -0.55
     which
    -0.54
    bewerken
    -0.49
    Personensuche
    -0.48
    ,
    -0.48
     whereby
    -0.47
     suivantes
    -0.46
    ?
    -0.45
    POSITIVE LOGITS
    "])
    0.90
    ")]
    0.81
     }</
    0.80
     we
    0.79
    mapStateToProps
    0.75
    chọn
    0.75
    "]);
    0.74
     they
    0.74
     there
    0.74
    )");
    0.73
    Act Density 0.133%

    No Known Activations