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

    Neuronpedia

    INDEX
    Explanations

    references to overarching concepts related to groups or collective experiences

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Hamm
    -0.66
    woff
    -0.54
     seng
    -0.52
    乓
    -0.49
     CORN
    -0.49
     Lumpur
    -0.48
    illes
    -0.48
     Dans
    -0.48
    cardname
    -0.48
     AssemblyTitle
    -0.48
    POSITIVE LOGITS
     conseguenza
    0.77
    tamment
    0.65
     szóci
    0.62
     veh
    0.62
    hasMoreElements
    0.60
    Revenir
    0.60
    thâu
    0.60
    mbic
    0.59
    ngdoc
    0.59
    complexContent
    0.59
    Act Density 0.011%

    No Known Activations