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

    Neuronpedia

    INDEX
    Explanations

    concepts related to clarity and structure in contexts such as budgets, designs, and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciaal
    -0.40
    енча
    -0.39
    astéroïdes
    -0.38
    antian
    -0.36
     Lei
    -0.36
    ConstraintMaker
    -0.36
    nit
    -0.36
     fällt
    -0.35
    ArrowToggle
    -0.34
    Kjelder
    -0.33
    POSITIVE LOGITS
     elegance
    0.66
    Flexibility
    0.65
     flexibility
    0.64
     Elegance
    0.63
     Geduld
    0.63
     firmness
    0.63
     specificity
    0.63
     stability
    0.62
     Tiefe
    0.62
    Stability
    0.62
    Act Density 1.037%

    No Known Activations