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

    Neuronpedia

    INDEX
    Explanations

    phrases related to first-time experiences and novelty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thog
    -0.53
     lunches
    -0.48
     chut
    -0.45
    цо
    -0.45
    IGraphics
    -0.43
    ceres
    -0.42
     Lucius
    -0.41
    ძ
    -0.40
     assi
    -0.40
    אס
    -0.40
    POSITIVE LOGITS
     unfamiliar
    1.02
     newcomer
    0.89
     novice
    0.86
     newcomers
    0.86
    Personensuche
    0.81
     novices
    0.81
     inconn
    0.79
     beginner
    0.79
     Roskov
    0.79
     المعيارى
    0.78
    Act Density 0.230%

    No Known Activations