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

    Neuronpedia

    INDEX
    Explanations

    references to "information" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rrggbb
    -0.73
    BagLayout
    -0.63
    ^(@)
    -0.58
    ConstraintMaker
    -0.57
     Valdés
    -0.56
    shadowOffset
    -0.56
     intervenir
    -0.54
    큼
    -0.54
    uxxxx
    -0.54
    äjä
    -0.54
    POSITIVE LOGITS
     technology
    0.66
     about
    0.65
     Technology
    0.64
    Données
    0.63
     Roskov
    0.63
    tainment
    0.62
     privilegi
    0.62
     gathered
    0.61
    merci
    0.57
     gleaned
    0.57
    Act Density 0.087%

    No Known Activations