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

    Neuronpedia

    INDEX
    Explanations

    the word "loyal" and related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    quick
    -0.66
    hazard
    -0.64
    paces
    -0.63
    LOD
    -0.62
     Puzz
    -0.60
    cloth
    -0.59
     Apocalypse
    -0.58
     concussion
    -0.57
    olson
    -0.56
     puberty
    -0.55
    POSITIVE LOGITS
     allegiance
    0.97
    ty
    0.94
     loyal
    0.93
    alty
    0.91
    hip
    0.87
     loyalty
    0.84
    alties
    0.82
     adherent
    0.82
    itness
    0.79
    oyal
    0.79
    Act Density 0.097%

    No Known Activations