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

    Neuronpedia

    INDEX
    Explanations

    references to undesirable effects and outcomes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.90
     Мексичка
    -0.72
    featureID
    -0.67
     schuldig
    -0.66
    XtraGrid
    -0.65
     Dostupné
    -0.65
     resourceCulture
    -0.62
    ConstraintMaker
    -0.61
    +#+#
    -0.60
    EndProject
    -0.59
    POSITIVE LOGITS
     unwanted
    0.77
     desired
    0.76
     disambiguazione
    0.64
     intended
    0.63
    desired
    0.62
    intended
    0.56
     undesirable
    0.55
     want
    0.54
    Desired
    0.54
     unintended
    0.52
    Act Density 0.455%

    No Known Activations